{
  "complete": true,
  "report": {
    "bucket": "vn_S_PLAY_reg",
    "label": "Strong Playful Style",
    "definition": {
      "id": "vn_S_PLAY_reg",
      "category": "talking_style",
      "head": "vn_S_PLAY_reg",
      "pole": "high",
      "label": "Strong Playful Style",
      "floor": 4.0,
      "canonical_dimension_name": "Playful Style"
    },
    "recipe_status": "direct_manual_recipe",
    "manual_provenance": [
      {
        "id": "rank4/style_s_play/full-v2-sealed/sealed-selected",
        "mission": "style_s_play",
        "format_status": "CANONICAL",
        "heldout": true,
        "qualified": true,
        "source_cfg": 3,
        "source_model": {
          "label": "Humaneness 1.5 + real-speech rank 4",
          "repo": "laion/Humaneness-Voice-Large-1.5-RealSpeech-LoRAs",
          "revision": "fed33e554f094fcdc89fc0124aed2f9d42018714",
          "rank": 4
        },
        "metrics": {
          "ce": 6.378604192733764,
          "genuineness": 4.167938842773437,
          "wer": 0.006754141238012205,
          "identity": 0.5668436245620251,
          "voiceclap": 0.06021118430420756,
          "fitness": 0.6654904914484826,
          "steering_v2": 0.6733305727810739,
          "raw_target": 2.897793610095978,
          "target_cdf": 0.6733305727810739,
          "family_hit_all": null,
          "nominal_hit_all": null,
          "n": 100,
          "valid_fraction": 1,
          "by_arm": {
            "reference": {
              "n": 50,
              "ce": 6.3881354331970215,
              "genuineness": 4.189779448509216,
              "wer": 0.006473118279569892,
              "identity": 0.5668436245620251,
              "fitness": 0.6839898945636871,
              "steering_v2": 0.7079369871065312
            },
            "none": {
              "n": 50,
              "ce": 6.369072952270508,
              "genuineness": 4.146098237037659,
              "wer": 0.007035164196454519,
              "identity": null,
              "fitness": 0.6469910883332781,
              "steering_v2": 0.6387241584556165
            }
          }
        }
      }
    ],
    "selected_wording": {
      "id": "manual-3fb618b13504",
      "general": "Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.",
      "inline": [
        "Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.",
        "Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.",
        "Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable."
      ],
      "cfg": 3,
      "recipe": "P06",
      "strategy": "initial-physical-directing",
      "timing_syntax": "canonical",
      "canonical_labels": true,
      "neutral_event": "keep",
      "parent": "cfg-3",
      "origin": "exact_frozen_manual_recipe"
    },
    "selection": {
      "manual_no_adapter": {
        "config": {
          "scale": 0.0,
          "cfg": 1.0
        },
        "n": 20,
        "target_z": 0.32917481149556344,
        "target_raw": 2.6965032696723936,
        "ce": 6.220981860160828,
        "genuineness": 4.2726232528686525,
        "identity": 0.5507739841938019,
        "wer": 0.0,
        "valid_fraction": 1,
        "identity_delta": -0.024085366725921632,
        "identity_pairs": 20,
        "gates_pass": true,
        "gate_scope": "development_provisional_20_pairs"
      },
      "manual_adapter": {
        "config": {
          "scale": 0.5,
          "cfg": 2.0
        },
        "n": 20,
        "target_z": 0.7005859416730451,
        "target_raw": 3.1793373227119446,
        "ce": 6.146519327163697,
        "genuineness": 4.165930557250976,
        "identity": 0.5313125804066658,
        "wer": 0.025188983488132095,
        "valid_fraction": 0.95,
        "identity_delta": -0.043546770513057706,
        "identity_pairs": 20,
        "gates_pass": true,
        "gate_scope": "development_provisional_20_pairs"
      },
      "grid": [
        {
          "config": {
            "scale": 0.0,
            "cfg": 1.0
          },
          "n": 20,
          "target_z": 0.32917481149556344,
          "target_raw": 2.6965032696723936,
          "ce": 6.220981860160828,
          "genuineness": 4.2726232528686525,
          "identity": 0.5507739841938019,
          "wer": 0.0,
          "valid_fraction": 1,
          "identity_delta": -0.024085366725921632,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 1.25
          },
          "n": 20,
          "target_z": 0.2946533074508346,
          "target_raw": 2.6516253530979155,
          "ce": 6.229917407035828,
          "genuineness": 4.212059497833252,
          "identity": 0.5557277366518975,
          "wer": 0.02,
          "valid_fraction": 0.95,
          "identity_delta": -0.01913161426782608,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 5.0
          },
          "n": 20,
          "target_z": 1.3001952924944575,
          "target_raw": 3.9588288068771362,
          "ce": 6.0760280847549435,
          "genuineness": 3.941405153274536,
          "identity": 0.457513689622283,
          "wer": 0.0952438080495356,
          "valid_fraction": 0.85,
          "identity_delta": -0.11734566129744053,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 4.0
          },
          "n": 20,
          "target_z": 1.1526367237737731,
          "target_raw": 3.767002832889557,
          "ce": 6.116734266281128,
          "genuineness": 4.043233954906464,
          "identity": 0.47334596067667006,
          "wer": 0.06903336773305813,
          "valid_fraction": 0.85,
          "identity_delta": -0.10151339024305343,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 3.0
          },
          "n": 20,
          "target_z": 1.0426269770304593,
          "target_raw": 3.6239902853965758,
          "ce": 6.205295085906982,
          "genuineness": 4.101914870738983,
          "identity": 0.49770529717206957,
          "wer": 0.02054502063983488,
          "valid_fraction": 0.95,
          "identity_delta": -0.07715405374765397,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 2.5
          },
          "n": 20,
          "target_z": 0.9305664069216274,
          "target_raw": 3.4783116698265077,
          "ce": 6.171141576766968,
          "genuineness": 4.114153182506561,
          "identity": 0.5095051527023315,
          "wer": 0.01488970588235294,
          "valid_fraction": 0.95,
          "identity_delta": -0.06535419821739197,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 1.5
          },
          "n": 20,
          "target_z": 0.627587886895229,
          "target_raw": 3.0844399333000183,
          "ce": 6.239448547363281,
          "genuineness": 4.234339416027069,
          "identity": 0.48349934443831444,
          "wer": 0.0027777777777777775,
          "valid_fraction": 1,
          "identity_delta": -0.09136000648140907,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.0,
            "cfg": 2.0
          },
          "n": 20,
          "target_z": 0.5988281349938163,
          "target_raw": 3.04705228805542,
          "ce": 6.194572496414184,
          "genuineness": 4.15871307849884,
          "identity": 0.5056926488876343,
          "wer": 0.04574819401444788,
          "valid_fraction": 0.95,
          "identity_delta": -0.06916670203208923,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 2.0
          },
          "n": 20,
          "target_z": 0.7005859416730451,
          "target_raw": 3.1793373227119446,
          "ce": 6.146519327163697,
          "genuineness": 4.165930557250976,
          "identity": 0.5313125804066658,
          "wer": 0.025188983488132095,
          "valid_fraction": 0.95,
          "identity_delta": -0.043546770513057706,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 1.5
          },
          "n": 20,
          "target_z": 0.6837158227818502,
          "target_raw": 3.157406187057495,
          "ce": 6.204500818252564,
          "genuineness": 4.175658416748047,
          "identity": 0.5623264029622078,
          "wer": 0.009444444444444445,
          "valid_fraction": 1,
          "identity_delta": -0.012532947957515717,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 1.25
          },
          "n": 20,
          "target_z": 0.6011474821004805,
          "target_raw": 3.050067436695099,
          "ce": 6.225151753425598,
          "genuineness": 4.219276857376099,
          "identity": 0.5302900657057762,
          "wer": 0.015789473684210527,
          "valid_fraction": 0.95,
          "identity_delta": -0.0445692852139473,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 1.0
          },
          "n": 20,
          "target_z": 0.3237304864540992,
          "target_raw": 2.689425653219223,
          "ce": 6.209663534164429,
          "genuineness": 4.194486558437347,
          "identity": 0.5451899543404579,
          "wer": 0.0,
          "valid_fraction": 1,
          "identity_delta": -0.029669396579265594,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 1.0
          },
          "n": 20,
          "target_z": 0.27700196356209034,
          "target_raw": 2.6286786258220673,
          "ce": 6.206486487388611,
          "genuineness": 4.265719616413117,
          "identity": 0.5424333319067955,
          "wer": 0.006458333333333333,
          "valid_fraction": 1,
          "identity_delta": -0.032426019012928006,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 5.0
          },
          "n": 20,
          "target_z": 1.448046859561524,
          "target_raw": 4.151035678386688,
          "ce": 6.0105010032653805,
          "genuineness": 4.014364087581635,
          "identity": 0.4288722038269043,
          "wer": 0.09244883040935672,
          "valid_fraction": 0.9,
          "identity_delta": -0.1459871470928192,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 4.0
          },
          "n": 20,
          "target_z": 1.342382845364969,
          "target_raw": 4.013672578334808,
          "ce": 6.067688274383545,
          "genuineness": 3.9663524627685547,
          "identity": 0.4120274199172854,
          "wer": 0.1244437994496044,
          "valid_fraction": 0.75,
          "identity_delta": -0.16283193100243806,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 4.0
          },
          "n": 20,
          "target_z": 1.3212890643447368,
          "target_raw": 3.9862506866455076,
          "ce": 6.061929869651794,
          "genuineness": 3.9330894351005554,
          "identity": 0.4064058978110552,
          "wer": 0.08322991916064672,
          "valid_fraction": 0.9,
          "identity_delta": -0.16845345310866833,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 5.0
          },
          "n": 20,
          "target_z": 1.2464843912265189,
          "target_raw": 3.8890046954154966,
          "ce": 5.936634206771851,
          "genuineness": 3.9254012942314147,
          "identity": 0.45370190143585204,
          "wer": 0.1047172772617819,
          "valid_fraction": 0.7,
          "identity_delta": -0.12115744948387146,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 5.0
          },
          "n": 20,
          "target_z": 1.2285156018960162,
          "target_raw": 3.8656452894210815,
          "ce": 5.767554569244385,
          "genuineness": 3.816668915748596,
          "identity": 0.3706980563700199,
          "wer": 0.15897467320261438,
          "valid_fraction": 0.75,
          "identity_delta": -0.2041612945497036,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 3.0
          },
          "n": 20,
          "target_z": 1.204492185870184,
          "target_raw": 3.834414875507355,
          "ce": 6.135796689987183,
          "genuineness": 4.067396628856659,
          "identity": 0.42851850762963295,
          "wer": 0.05746968524251806,
          "valid_fraction": 0.95,
          "identity_delta": -0.14634084329009056,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 3.0
          },
          "n": 20,
          "target_z": 1.1916015882725834,
          "target_raw": 3.8176571130752563,
          "ce": 6.101246047019958,
          "genuineness": 3.9304221510887145,
          "identity": 0.45732354670763015,
          "wer": 0.009791666666666667,
          "valid_fraction": 1,
          "identity_delta": -0.11753580421209335,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 4.0
          },
          "n": 20,
          "target_z": 1.1299805019283953,
          "target_raw": 3.7375497698783873,
          "ce": 6.06192979812622,
          "genuineness": 3.989573800563812,
          "identity": 0.4453650988638401,
          "wer": 0.030268317853457172,
          "valid_fraction": 0.95,
          "identity_delta": -0.1294942520558834,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 3.0
          },
          "n": 20,
          "target_z": 1.1145507992943904,
          "target_raw": 3.7174911737442016,
          "ce": 6.149894976615906,
          "genuineness": 4.053903245925904,
          "identity": 0.4551479905843735,
          "wer": 0.05889189886480908,
          "valid_fraction": 0.85,
          "identity_delta": -0.11971136033535004,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 2.5
          },
          "n": 20,
          "target_z": 1.0132812651160947,
          "target_raw": 3.5858408927917482,
          "ce": 6.182857060432434,
          "genuineness": 4.031623315811157,
          "identity": 0.4829692915081978,
          "wer": 0.03036958204334365,
          "valid_fraction": 0.95,
          "identity_delta": -0.09189005941152573,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 2.5
          },
          "n": 20,
          "target_z": 1.0058593983905448,
          "target_raw": 3.5761924743652345,
          "ce": 6.15485908985138,
          "genuineness": 4.005263864994049,
          "identity": 0.486100535094738,
          "wer": 0.03886480908152735,
          "valid_fraction": 0.95,
          "identity_delta": -0.0887588158249855,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 2.5
          },
          "n": 20,
          "target_z": 0.9476562745726091,
          "target_raw": 3.5005284786224364,
          "ce": 6.144732189178467,
          "genuineness": 4.093128490447998,
          "identity": 0.4930114924907684,
          "wer": 0.04593201754385965,
          "valid_fraction": 0.95,
          "identity_delta": -0.08184785842895508,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 2.0
          },
          "n": 20,
          "target_z": 0.850585918748162,
          "target_raw": 3.3743371248245237,
          "ce": 6.149894952774048,
          "genuineness": 4.105680537223816,
          "identity": 0.4806120231747627,
          "wer": 0.02894736842105263,
          "valid_fraction": 0.95,
          "identity_delta": -0.09424732774496078,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 2.0
          },
          "n": 20,
          "target_z": 0.7057372912930102,
          "target_raw": 3.186034071445465,
          "ce": 6.195366716384887,
          "genuineness": 4.099090683460235,
          "identity": 0.5126369953155517,
          "wer": 0.05979166666666667,
          "valid_fraction": 0.95,
          "identity_delta": -0.062222355604171754,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 1.5
          },
          "n": 20,
          "target_z": 0.5971435779011829,
          "target_raw": 3.0448623657226563,
          "ce": 6.197352409362793,
          "genuineness": 4.158085453510284,
          "identity": 0.4814432352781296,
          "wer": 0.003125,
          "valid_fraction": 1,
          "identity_delta": -0.09341611564159394,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.5,
            "cfg": 1.5
          },
          "n": 20,
          "target_z": 0.5425659143117386,
          "target_raw": 2.973911464214325,
          "ce": 6.231505918502807,
          "genuineness": 4.16734265089035,
          "identity": 0.4741486631333828,
          "wer": 0.012549019607843137,
          "valid_fraction": 1,
          "identity_delta": -0.10071068778634071,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 1.25
          },
          "n": 20,
          "target_z": 0.5337890586135159,
          "target_raw": 2.962501561641693,
          "ce": 6.203706550598144,
          "genuineness": 4.234966993331909,
          "identity": 0.5180474758148194,
          "wer": 0.003333333333333333,
          "valid_fraction": 1,
          "identity_delta": -0.05681187510490417,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 1.0,
            "cfg": 1.25
          },
          "n": 20,
          "target_z": 0.44875488999219726,
          "target_raw": 2.8519572377204896,
          "ce": 6.1878211975097654,
          "genuineness": 4.159654521942139,
          "identity": 0.5035475984215736,
          "wer": 0.012916666666666667,
          "valid_fraction": 1,
          "identity_delta": -0.07131175249814987,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "config": {
            "scale": 0.75,
            "cfg": 1.0
          },
          "n": 20,
          "target_z": 0.24372558786507073,
          "target_raw": 2.585419374704361,
          "ce": 6.1921896696090695,
          "genuineness": 4.234653186798096,
          "identity": 0.5159410938620568,
          "wer": 0.0,
          "valid_fraction": 1,
          "identity_delta": -0.058918257057666776,
          "identity_pairs": 20,
          "gates_pass": false,
          "gate_scope": "development_provisional_20_pairs"
        }
      ],
      "development_standard": [
        {
          "scale": 0.0,
          "n": 20,
          "target_z": -0.4281249985671948,
          "target_raw": 1.712014365196228,
          "ce": 6.185438394546509,
          "genuineness": 4.23590841293335,
          "identity": 0.5748593509197235,
          "wer": 0.0,
          "valid_fraction": 1,
          "identity_delta": 0.0,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "scale": 0.5,
          "n": 20,
          "target_z": -0.4194824230794519,
          "target_raw": 1.7232497036457062,
          "ce": 6.194175338745117,
          "genuineness": 4.262267780303955,
          "identity": 0.550463055819273,
          "wer": 0.002631578947368421,
          "valid_fraction": 1,
          "identity_delta": -0.024396295100450514,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "scale": 0.75,
          "n": 20,
          "target_z": -0.41903074786195665,
          "target_raw": 1.7238368809223175,
          "ce": 6.171538710594177,
          "genuineness": 4.272623181343079,
          "identity": 0.5698726862668991,
          "wer": 0.003333333333333333,
          "valid_fraction": 1,
          "identity_delta": -0.004986664652824402,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        },
        {
          "scale": 1.0,
          "n": 20,
          "target_z": -0.4734375064476234,
          "target_raw": 1.6531081557273866,
          "ce": 6.1369880676269535,
          "genuineness": 4.251598525047302,
          "identity": 0.580569076538086,
          "wer": 0.0,
          "valid_fraction": 1,
          "identity_delta": 0.005709725618362427,
          "identity_pairs": 20,
          "gates_pass": true,
          "gate_scope": "development_provisional_20_pairs"
        }
      ]
    },
    "heldout": {
      "standard": {
        "n": 50,
        "target_z": -0.3973535129769969,
        "target_raw": 1.752017261981964,
        "ce": 6.250091753005981,
        "genuineness": 4.30099091053009,
        "identity": 0.5770703337341547,
        "wer": 0.007453416149068323,
        "valid_fraction": 1,
        "identity_delta": 0.0,
        "identity_pairs": 50,
        "gates_pass": true,
        "gate_scope": "heldout_50_reference_pairs"
      },
      "manual": {
        "n": 50,
        "target_z": -0.05236571680928542,
        "target_raw": 2.200501010417938,
        "ce": 6.268836431503296,
        "genuineness": 4.264840903282166,
        "identity": 0.5568684732913971,
        "wer": 0.006421513269339356,
        "valid_fraction": 1,
        "identity_delta": -0.020201860442757607,
        "identity_pairs": 50,
        "gates_pass": true,
        "gate_scope": "heldout_50_reference_pairs"
      },
      "adapter": {
        "n": 50,
        "target_z": 0.45795899765441767,
        "target_raw": 2.863922567367554,
        "ce": 6.2791619300842285,
        "genuineness": 4.227059121131897,
        "identity": 0.5882936984300613,
        "wer": 0.013177608051749928,
        "valid_fraction": 0.98,
        "identity_delta": 0.01122336469590664,
        "identity_pairs": 50,
        "gates_pass": true,
        "gate_scope": "heldout_50_reference_pairs"
      },
      "matched_no_adapter": {
        "n": 50,
        "target_z": 0.45413086495308974,
        "target_raw": 2.858945999145508,
        "ce": 6.280273895263672,
        "genuineness": 4.217896122932434,
        "identity": 0.551513960659504,
        "wer": 0.022128740824392996,
        "valid_fraction": 0.98,
        "identity_delta": -0.025556373074650765,
        "identity_pairs": 50,
        "gates_pass": true,
        "gate_scope": "heldout_50_reference_pairs"
      }
    },
    "adapter_vs_matched_cfg": {
      "n": 50,
      "delta_z": 0.0038281327013279334,
      "ci95_z": [
        -0.08579100154321143,
        0.09344726694586729
      ],
      "language_deltas": {
        "en": 0.004345714206852693,
        "de": 0.1358398728090804,
        "fr": -0.14379880535682993,
        "nl": -0.07285155560462499,
        "es": 0.0956054374521615
      },
      "languages_improved": 3,
      "clear_gain": false,
      "delta_ce": -0.0011119651794433594,
      "delta_genuineness": 0.009162998199462891,
      "delta_wer": -0.008951132772643068,
      "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets."
    },
    "adapter_vs_best_manual": {
      "n": 50,
      "delta_z": 0.5103247144637031,
      "ci95_z": [
        0.38474607986790865,
        0.6305005061355698
      ],
      "language_deltas": {
        "en": 0.39003904657795224,
        "de": 0.6644531622171149,
        "fr": 0.5670532657825671,
        "nl": 0.301806627510355,
        "es": 0.6282714702305262
      },
      "languages_improved": 5,
      "clear_gain": true,
      "delta_ce": 0.010325498580932617,
      "delta_genuineness": -0.037781782150268554,
      "delta_wer": 0.006756094782410572,
      "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets."
    },
    "manual_vs_standard": {
      "n": 50,
      "delta_z": 0.34498779616771147,
      "ci95_z": [
        0.2321386669327176,
        0.4781665100285818
      ],
      "language_deltas": {
        "en": 0.5919922466211244,
        "de": 0.17011717641366983,
        "fr": 0.40228268563355346,
        "nl": 0.3006347625041712,
        "es": 0.25991210966603856
      },
      "languages_improved": 5,
      "clear_gain": true,
      "delta_ce": 0.018744678497314454,
      "delta_genuineness": -0.036150007247924804,
      "delta_wer": -0.0010319028797289667,
      "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets."
    },
    "route": {
      "adapter": false,
      "scale": 0.0,
      "cfg": 1.0,
      "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain"
    },
    "reference_only": true,
    "updated": 1793034360.7208743,
    "example": {
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "language": "fr",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "frames": 128,
      "reference": true
    }
  },
  "rows": [
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "0091b6271835e2243b01c88dc51057ce161df1f8deb52c4bbc14afaeaf3928ec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "f25e099af10db28cd2ec2eca37b101edaba5d780468f5f3ec8aabe050ed63a79",
      "generation_seconds_batch": 19.65025817102287,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.320137023925781,
        "target_z": 1.5781249297925455,
        "ce": 6.356205940246582,
        "genuineness": 4.287685871124268,
        "identity": 0.5645559430122375,
        "hypothesis": "Yes! J'ai trouvé la petite boite. Elle était prêt de la vie fenêtre. We've regarded ensemble what contained.",
        "wer": 0.5263157894736842,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0091b6271835e2243b01c88dc51057ce161df1f8deb52c4bbc14afaeaf3928ec.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "00d5d868af0fcaaab325369d9137ebf98a1cecd40119c9284754f744baeca6b6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "14a7cf3c5d8a8af43d5512609cf362ee080aab28dc1b86deed074602d3e841bf",
      "generation_seconds_batch": 23.728623947012238,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7310752868652344,
        "target_z": 1.1250001260868572,
        "ce": 5.792276382446289,
        "genuineness": 3.9299514293670654,
        "identity": 0.4856041669845581,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/00d5d868af0fcaaab325369d9137ebf98a1cecd40119c9284754f744baeca6b6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "01a21b8c1fb86977c1116aef1ab1f8c4ed6e100f76b7dc7432329cbf40adac78",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "e7b737779758fb0b8fcf4dbf1e04b79e2c772e322af99fba376414fabc950a40",
      "generation_seconds_batch": 21.052851790911518,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.954512596130371,
        "target_z": 1.2968751275196624,
        "ce": 6.292664527893066,
        "genuineness": 4.3127899169921875,
        "identity": 0.6595995426177979,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/01a21b8c1fb86977c1116aef1ab1f8c4ed6e100f76b7dc7432329cbf40adac78.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "68849ea5a0b55e6607029ea337c1f85e69a49285ee37361528f2e200ee863937",
      "generation_seconds_batch": 18.18009824794717,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6900603771209717,
        "target_z": 0.32421873603014933,
        "ce": 6.062326908111572,
        "genuineness": 4.469690799713135,
        "identity": 0.7435660362243652,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "020ddd382004a1cdaaa1e13e24731f24be62c1b83a90455bb92e6673593781d5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "52af05e92ff8b03d36bc5025c5cd3bc0c0b5059c79a7970286f48e80ec1746ea",
      "generation_seconds_batch": 18.47205436602235,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.530099630355835,
        "target_z": 0.20117190168599677,
        "ce": 6.205295085906982,
        "genuineness": 4.331617832183838,
        "identity": 0.6106045246124268,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lise-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.045454545454545456,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/020ddd382004a1cdaaa1e13e24731f24be62c1b83a90455bb92e6673593781d5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "029a991e1f8e3e65e2e12fbabe8e3d081269f1e7640b4a732da6bfcec45c16c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "4b9c146c2916edf5e036866cfd1703526660e1ec30f87e6f6a789568f19d8aa3",
      "generation_seconds_batch": 24.433534902054816,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7176003456115723,
        "target_z": -0.42382808685156165,
        "ce": 6.1020402908325195,
        "genuineness": 4.2374773025512695,
        "identity": 0.6065603494644165,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/029a991e1f8e3e65e2e12fbabe8e3d081269f1e7640b4a732da6bfcec45c16c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "02f8a0d85a814145c26dad964d52d9ddb2a475bb082a7bf45cb5728719373eb9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fae007418fb7898565d463396df4747ecb2b33ef37df284010318f6547add253",
      "generation_seconds_batch": 23.953770341002382,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.599043846130371,
        "target_z": 1.0234373918232078,
        "ce": 6.395919322967529,
        "genuineness": 4.243753433227539,
        "identity": 0.3929251730442047,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/02f8a0d85a814145c26dad964d52d9ddb2a475bb082a7bf45cb5728719373eb9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "03c7d77a5f249c2418b8737f548e841ea82bf2c02029aaadd6f239b5b2148283",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "10deb10dbabb207df2204114dddb065c9cacf7ab3e5e70cd352fd48c90ec494e",
      "generation_seconds_batch": 20.07518050901126,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.420285224914551,
        "target_z": 0.11669920930244074,
        "ce": 6.117925643920898,
        "genuineness": 4.243753433227539,
        "identity": 0.7535478472709656,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/03c7d77a5f249c2418b8737f548e841ea82bf2c02029aaadd6f239b5b2148283.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "03cf811480630ee713ac00876aa354cb031c6414e9d59cd6d451487024ba6817",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ba13f660348fcd7575c255c6a6216fca5f32a2c5b12b76f4ac162aef846b9e16",
      "generation_seconds_batch": 22.462294909986667,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5584189891815186,
        "target_z": 0.9921874749259091,
        "ce": 6.2767791748046875,
        "genuineness": 4.18726921081543,
        "identity": 0.619928240776062,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/03cf811480630ee713ac00876aa354cb031c6414e9d59cd6d451487024ba6817.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "045b189aae9d6ca19b93ba9ff1d90989c430ce08d65584bdd3c1b95b0920babb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c45bb399c9f3fcbb587e09af28d70724f29f70903b9af76f240176399dc28cca",
      "generation_seconds_batch": 17.50111776497215,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.934199810028076,
        "target_z": 1.2812498939724155,
        "ce": 6.308549880981445,
        "genuineness": 4.444586753845215,
        "identity": 0.4697340130805969,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/045b189aae9d6ca19b93ba9ff1d90989c430ce08d65584bdd3c1b95b0920babb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "04736ae5a0fd943c5afe4b344b1448cdd1c4dbcfb9c2cc4c3cc0dcfc05d99ea4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e078c677f3e33d8d19e600304437590b39d3a1c84af68923e568293881dd52f3",
      "generation_seconds_batch": 18.08075435901992,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.348263263702393,
        "genuineness": 4.331617832183838,
        "identity": 0.3973345458507538,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/04736ae5a0fd943c5afe4b344b1448cdd1c4dbcfb9c2cc4c3cc0dcfc05d99ea4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "055dd3c560fdb11e3476b5688f6e36970e43bdb07813ebd393aef089c5608fb0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "76b3e7ffce249ac8dff4836f556124895ab9000ffdf190022149eac28df16d83",
      "generation_seconds_batch": 17.272471650969237,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5787315368652344,
        "target_z": 1.007812525074091,
        "ce": 6.125868320465088,
        "genuineness": 4.15588903427124,
        "identity": 0.6500208973884583,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/055dd3c560fdb11e3476b5688f6e36970e43bdb07813ebd393aef089c5608fb0.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3a2aef076f8449f96ed711736738b2c635a84c977f76b52cdcd824dcdc3e72d6",
      "generation_seconds_batch": 18.345194073976018,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2114474773406982,
        "target_z": -0.04394535037978737,
        "ce": 6.332377910614014,
        "genuineness": 4.632867813110352,
        "identity": 0.5588618516921997,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "05bf5cd56db10b52d7d491ef790e2378c1e9081627c70665962d4d3a027fa3f8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5a3541d5006228e3a007b671d264b7bd8359c684877bf9d48c0f5aee9a454741",
      "generation_seconds_batch": 18.058475482976064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 6.467403411865234,
        "genuineness": 3.911123275756836,
        "identity": 0.5803322196006775,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/05bf5cd56db10b52d7d491ef790e2378c1e9081627c70665962d4d3a027fa3f8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "05c57dda0248a9b750c80aa24d8c68e1e67d3ae07bbbc4f53bda0d5886a9443a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "b19d9f8e6b291414e11b4a5a655b45703e2a23e5219ceca198b3c632f05e8bac",
      "generation_seconds_batch": 17.92609799595084,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0912318229675293,
        "target_z": 0.6328124219121168,
        "ce": 6.062326908111572,
        "genuineness": 4.444586753845215,
        "identity": 0.6044961214065552,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/05c57dda0248a9b750c80aa24d8c68e1e67d3ae07bbbc4f53bda0d5886a9443a.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "06e7d45c40290b3824abcaacedc86579996b1a84522913050a0b857e77622eda",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "51b41632e5ca78aef0aed97b945bcca24276b38936ef72e174a42b30e0af0d6e",
      "generation_seconds_batch": 20.668333042995073,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3974337577819824,
        "target_z": 0.09912114251015183,
        "ce": 6.165581703186035,
        "genuineness": 4.482243061065674,
        "identity": 0.5512642860412598,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand il a un moment.",
        "wer": 0.09090909090909091,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/06e7d45c40290b3824abcaacedc86579996b1a84522913050a0b857e77622eda.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "07523003a9cffa6f644b6ff6c69ffce4548f7488251beb85a2782961af85c973",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a8504e07f3ef41acc1e9e6d7f26af805a798db9bacd57763cae90e7b3cb9123a",
      "generation_seconds_batch": 24.12866352405399,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.241281509399414,
        "target_z": -0.020996075168307614,
        "ce": 6.348263263702393,
        "genuineness": 4.036643981933594,
        "identity": 0.37368544936180115,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/07523003a9cffa6f644b6ff6c69ffce4548f7488251beb85a2782961af85c973.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "07a8b65ef788ef9cae63b88fdb4061f4cc07bc796ae69835ad75cdb2e572f039",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9c35d962b859fd47dd0a00c33d1270161bb4279bbc4768834f20aceb6d9f38b9",
      "generation_seconds_batch": 24.541802480001934,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.233419418334961,
        "target_z": 0.7421875895503247,
        "ce": 6.229123115539551,
        "genuineness": 4.394378662109375,
        "identity": 0.42376285791397095,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/07a8b65ef788ef9cae63b88fdb4061f4cc07bc796ae69835ad75cdb2e572f039.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "07c0a7b304064f12111a6a592f49e1d9dc8b8a877ae3d3c1782e00b406066526",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8f10e1ac5317822773670501a03dfd89c0283e1cff2273f3a3ed79c0661aff1e",
      "generation_seconds_batch": 24.032604067004286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.593576192855835,
        "target_z": 0.2500000687746494,
        "ce": 6.3641486167907715,
        "genuineness": 4.293961524963379,
        "identity": 0.584071159362793,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/07c0a7b304064f12111a6a592f49e1d9dc8b8a877ae3d3c1782e00b406066526.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "07c1e64810ea4259af673f9e52e06a2c185ee465a0b4bb5fa7ec26ccf5395676",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eed3b77d20b03db5e5e882211fe81047098f82deaecdf92ec7c801bc8a1a5f43",
      "generation_seconds_batch": 22.834648262010887,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7484588623046875,
        "target_z": 0.36914068643152276,
        "ce": 6.300607204437256,
        "genuineness": 4.2374773025512695,
        "identity": 0.5077219009399414,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/07c1e64810ea4259af673f9e52e06a2c185ee465a0b4bb5fa7ec26ccf5395676.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "07eb48b8378406e72595b7c29ff536e97b4a197ebbe06aa175697d46cc012d52",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5d390d7657c4fb90a671e80117ee091542f04323bb3efffd292936cb1e9037ab",
      "generation_seconds_batch": 19.035375859006308,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1784398555755615,
        "target_z": -0.06933585054663467,
        "ce": 6.308549880981445,
        "genuineness": 3.9676074981689453,
        "identity": 0.19710104167461395,
        "hypothesis": "I wrote the number on the envelope, read it carefully, and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/07eb48b8378406e72595b7c29ff536e97b4a197ebbe06aa175697d46cc012d52.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "084007e261110c7c665d5b3173accab6b128bf015f4587a416bbe84af010de55",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e01e6347829d06aea3851b1ce305c94f9df3a991144830fa05bab7403074886f",
      "generation_seconds_batch": 23.528223672998138,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 6.125868320465088,
        "genuineness": 3.936227321624756,
        "identity": 0.5497428178787231,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/084007e261110c7c665d5b3173accab6b128bf015f4587a416bbe84af010de55.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "086af1d847fa0c82dc4188b956a71172be2e4d4efa1cd1c8804c31bec8dc6dfa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "35af856338926beb5bedf4cab65da6a8213be0cc56c7f891eb2269bc208dee51",
      "generation_seconds_batch": 27.672645198064856,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7920126914978027,
        "target_z": 1.1718750931323378,
        "ce": 6.340320587158203,
        "genuineness": 4.2249250411987305,
        "identity": 0.6057308912277222,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/086af1d847fa0c82dc4188b956a71172be2e4d4efa1cd1c8804c31bec8dc6dfa.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "087f306a46bd27dd049eed0855e3716047b7bf203b99edead816a33fde5cedd6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "139d461281ce2a65db90232e84bb9bf48f6f207470f333525ffc1ecc58ecb951",
      "generation_seconds_batch": 29.312737667001784,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.467012882232666,
        "target_z": 0.9218750243576883,
        "ce": 6.284721851348877,
        "genuineness": 4.268857479095459,
        "identity": 0.5208362340927124,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/087f306a46bd27dd049eed0855e3716047b7bf203b99edead816a33fde5cedd6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "08f0688a7104c51e8893397234011ec11c466e14d451a6fda9f1d8f60872e751",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "882282e4c29ba35dc73ffaa3b0b6216c826d6b8851485977c156abe4bf099974",
      "generation_seconds_batch": 17.66493027098477,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.700606346130371,
        "target_z": 1.101562459165052,
        "ce": 5.927301406860352,
        "genuineness": 3.835810661315918,
        "identity": 0.4977792501449585,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/08f0688a7104c51e8893397234011ec11c466e14d451a6fda9f1d8f60872e751.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "0927661a11546814b3cc6abd36be9774eae56939f6878acc220914e901675bfa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "28d79f02d9f7fdd031ead8e5312b79f8d3a34634dfba3f9e62851b0ff91c7fa3",
      "generation_seconds_batch": 31.32850005000364,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.385762929916382,
        "target_z": 0.8593750071640259,
        "ce": 6.324435234069824,
        "genuineness": 4.005263805389404,
        "identity": 0.3574296832084656,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0927661a11546814b3cc6abd36be9774eae56939f6878acc220914e901675bfa.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "0931b1fb12d863072273e65a05c40679d66a5756c89693b13ac3234a0ec3736a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "22850bbd7830955315703def70af61de2dd6c9721ef926e7c748b76843b836f0",
      "generation_seconds_batch": 23.8706452610204,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 6.332377910614014,
        "genuineness": 4.231201171875,
        "identity": 0.5258718729019165,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what contiene.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0931b1fb12d863072273e65a05c40679d66a5756c89693b13ac3234a0ec3736a.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "097e3c838c5ea050351058506cad893248e61531edddad2b861360abc8e0a9d8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b308de882667745c369ef069ad1698320c07d3293cbbdfb14f7e0652e36ba0a2",
      "generation_seconds_batch": 18.09012217808049,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.2021710872650146,
        "target_z": -0.8203124734931039,
        "ce": 6.109982967376709,
        "genuineness": 3.8671910762786865,
        "identity": 0.7728798389434814,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/097e3c838c5ea050351058506cad893248e61531edddad2b861360abc8e0a9d8.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "098af7953841fe2669ae4d5b1f13f68cc63d9045707310516e9f121667077af4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "945d6796d933b650115e43a0ccdec02b9e4fbd01895ff763a9919560499a17b5",
      "generation_seconds_batch": 22.474340933025815,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.1894097328186035,
        "genuineness": 4.231201171875,
        "identity": 0.6725831627845764,
        "hypothesis": "Quelqu'un j'ai déplacé la petite chaise bleue. Elle is ici, près de la grande bibliothèque. We remettrons after le déjeuner.",
        "wer": 0.23809523809523808,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/098af7953841fe2669ae4d5b1f13f68cc63d9045707310516e9f121667077af4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "09a79d877f852963bc99b448610569871eedb4d90e7ba27a5d63a7a9b9ced0c2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a68625f304a2c8cdb0ce947d9118b4ac71110ce2eeb96054cfabb6770132955c",
      "generation_seconds_batch": 31.469926080084406,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.674826145172119,
        "target_z": 0.31250008596831175,
        "ce": 6.332377910614014,
        "genuineness": 4.369274139404297,
        "identity": 0.4812082052230835,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/09a79d877f852963bc99b448610569871eedb4d90e7ba27a5d63a7a9b9ced0c2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "0a261f3f51860d04c232982314346facbd5a9315bf6a0e68658c265716762e12",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d7c925bcdc3c8e90b6bd192cbe6d35a23dd366cb178a1e67237c6554d556b7d1",
      "generation_seconds_batch": 18.13812586606946,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9951374530792236,
        "target_z": 1.328125044416961,
        "ce": 6.109982967376709,
        "genuineness": 3.810706615447998,
        "identity": 0.49877655506134033,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0a261f3f51860d04c232982314346facbd5a9315bf6a0e68658c265716762e12.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "0a8b86e8e5abfec8b2956695624462b56a6b9b234103207f52e8972cf79d2914",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "31f75d6c5148a1cd429464a9d9e9554a71ba0f44332aba2f54fa89ffd506b710",
      "generation_seconds_batch": 25.21353465190623,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.556759834289551,
        "target_z": 0.2216797685430439,
        "ce": 6.117925643920898,
        "genuineness": 4.419482707977295,
        "identity": 0.6572506427764893,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0a8b86e8e5abfec8b2956695624462b56a6b9b234103207f52e8972cf79d2914.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "0a8c9784589606c6bf8fa650f5fcbb4947515a3817c3dfee5d2cc12bdde900a4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9a49ecfffacdab70f82262db73b3465f21fb30f6a86ee9bd333cd74e04cbfd64",
      "generation_seconds_batch": 24.042632439988665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7920126914978027,
        "target_z": 1.1718750931323378,
        "ce": 6.332377910614014,
        "genuineness": 3.8169827461242676,
        "identity": 0.4086681306362152,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0a8c9784589606c6bf8fa650f5fcbb4947515a3817c3dfee5d2cc12bdde900a4.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "0a8e84af3de68ffeac420c4949a55e2ac5fb4370a8cb6440e635b1b35243a771",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "69b275e911858fb895de45d4a5eac4fb5cc1c6a1d2d288e04ab7fe8d1119f290",
      "generation_seconds_batch": 22.811471040011384,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.162325620651245,
        "target_z": 0.6875000057312208,
        "ce": 6.340320587158203,
        "genuineness": 4.400654315948486,
        "identity": 0.6640549898147583,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0a8e84af3de68ffeac420c4949a55e2ac5fb4370a8cb6440e635b1b35243a771.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "0b498279ef267a9d693272f9b5e0b199e4103e945fb8194fda6dc3765a29050a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a50ca2e69e64bb648f68eb807d8bde321ecad703824f657727a9fb089f2f2845",
      "generation_seconds_batch": 24.613500033970922,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9486547708511353,
        "target_z": -0.24609376038783767,
        "ce": 6.356205940246582,
        "genuineness": 4.319066047668457,
        "identity": 0.5452808141708374,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0b498279ef267a9d693272f9b5e0b199e4103e945fb8194fda6dc3765a29050a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "0c0c6ff31c8e82ecf15a5043a9b5b08e96adf04ef3fcd4bfb652be8da3faf075",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2f2da535c8146d2ec467ce5dad250eaa32023cd57837e08056f981be8eebc229",
      "generation_seconds_batch": 24.78066837589722,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.4013872146606445,
        "target_z": 1.6406251303852728,
        "ce": 6.046441555023193,
        "genuineness": 4.024092197418213,
        "identity": 0.4037519693374634,
        "hypothesis": "Encontrada, cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.17647058823529413,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0c0c6ff31c8e82ecf15a5043a9b5b08e96adf04ef3fcd4bfb652be8da3faf075.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "0c4b9f59f865b6f923ea4884f5cf599f00e2e785a6ea0ff36f543bac3deb6c9f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "db8c9062f218f076f0a0972df0621c0fb64f9638698c3deef0b7809fcfa16c1f",
      "generation_seconds_batch": 31.32850005000364,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5787315368652344,
        "target_z": 1.007812525074091,
        "ce": 6.268836498260498,
        "genuineness": 3.4718005657196045,
        "identity": 0.34592247009277344,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0c4b9f59f865b6f923ea4884f5cf599f00e2e785a6ea0ff36f543bac3deb6c9f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "0c58a54b1ea18503e0519bc87cb8e82ce3f525f4bbfbf30119245499def4b62a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1677b2c83b66d8d29c5a496b50ff242fe4107e0bc1620e4b15f462261ea95737",
      "generation_seconds_batch": 24.43482965999283,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6396689414978027,
        "target_z": 1.0546874921195715,
        "ce": 6.109982967376709,
        "genuineness": 3.9801597595214844,
        "identity": 0.16389068961143494,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0c58a54b1ea18503e0519bc87cb8e82ce3f525f4bbfbf30119245499def4b62a.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "0c93e5c221e46a04c005bd43a62c3b9405dad4264854c265fb614269b538495c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a7e9abd2231cf37d88daba4d1d86f218c7a02e8d6e054c78b85925f758247133",
      "generation_seconds_batch": 24.68801408598665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3451380729675293,
        "target_z": 0.8281250902667273,
        "ce": 6.348263263702393,
        "genuineness": 4.105680465698242,
        "identity": 0.48239976167678833,
        "hypothesis": "The keys are on the kitchen table. I check the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.043478260869565216,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0c93e5c221e46a04c005bd43a62c3b9405dad4264854c265fb614269b538495c.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e191ae2d714d5f32800c1dcd9673cc7dca10e2e87cdfe9f4a1a5df3edb1fbb5f",
      "generation_seconds_batch": 18.169685131055303,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.004124402999878,
        "target_z": -0.9726562080904481,
        "ce": 6.197352409362793,
        "genuineness": 4.036643981933594,
        "identity": 0.5778496265411377,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "0d32e8ad77e6b4b2e46520ec0bb0ec06391bcb60fba3d53ec502bae9cf4446e6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0d7023647d2e57b2bd797d4f8195706ada9d6e6c8352cef8adde092922ea9f65",
      "generation_seconds_batch": 25.080600660992786,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8935749530792236,
        "target_z": 1.249999977075117,
        "ce": 6.1894097328186035,
        "genuineness": 4.017816066741943,
        "identity": 0.5826151967048645,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0d32e8ad77e6b4b2e46520ec0bb0ec06391bcb60fba3d53ec502bae9cf4446e6.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "0da50fc900df8894263b0b8ed4ae6ffb11c385be8531123d90c2b649c6619d6c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "848f18ed9c30e13136c0d570ce38a364c8380ac217f4af90edce75991d9b240f",
      "generation_seconds_batch": 16.45483191299718,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.005293846130371,
        "target_z": 1.3359376611905847,
        "ce": 6.1894097328186035,
        "genuineness": 4.055472373962402,
        "identity": 0.619605541229248,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0da50fc900df8894263b0b8ed4ae6ffb11c385be8531123d90c2b649c6619d6c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "0dd08bf3002b3fd2db9e6f084aff750598fc2bbb10b28dc6bb48e43e41a4e5b4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7d594f8e4aa16b645f71276e990561de76917077d332e342f2c788c2cb26700d",
      "generation_seconds_batch": 24.73492790898308,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3669650554656982,
        "target_z": 0.07568365898741158,
        "ce": 6.1894097328186035,
        "genuineness": 3.886019229888916,
        "identity": 0.2790801525115967,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0dd08bf3002b3fd2db9e6f084aff750598fc2bbb10b28dc6bb48e43e41a4e5b4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "0ea74119c7de4d9cc21a6a9c28d2b4c07871ce4cb489fad2d48ba8e32ddc8133",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "2f6d564a40b7f267a948efb92cbf0323c81a495972c6c4a9350dc48939bf1502",
      "generation_seconds_batch": 22.431398672051728,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.5029497146606445,
        "target_z": 1.7187501977271171,
        "ce": 5.935244083404541,
        "genuineness": 4.099404335021973,
        "identity": 0.39067789912223816,
        "hypothesis": "¡Ey! Que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que es.",
        "wer": 0.23529411764705882,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0ea74119c7de4d9cc21a6a9c28d2b4c07871ce4cb489fad2d48ba8e32ddc8133.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "0ef71c89cc2db4d714c7282b08728844ed7ebf8b4a296831fef87ed3861fca5b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "37bb59d93d23644717eca78322adc8b3d7b64ff9483b8e33547a92732510c1d5",
      "generation_seconds_batch": 16.672924345941283,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.131856918334961,
        "target_z": 0.6640625222084805,
        "ce": 6.173524379730225,
        "genuineness": 4.3127899169921875,
        "identity": 0.7890371084213257,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0ef71c89cc2db4d714c7282b08728844ed7ebf8b4a296831fef87ed3861fca5b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "0f36ffbe11f6dafc91e384af44be77a680fafbcf17f17b2a85c178795d699342",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f2040c4e83a5198b2d4f36ed7251478b45584b180f8281910400694df59fa5f1",
      "generation_seconds_batch": 22.061856417101808,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.346017837524414,
        "target_z": 0.059570400527969226,
        "ce": 6.443574905395508,
        "genuineness": 4.193545341491699,
        "identity": 0.7201417684555054,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/0f36ffbe11f6dafc91e384af44be77a680fafbcf17f17b2a85c178795d699342.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "100e33bcf8cb00897f1f68bd93e0dd0b0ef87b00fa9029a49fdd93d0b1cfc206",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "33683ab0b421211c624ffef494632cf5743cc4000fb14aaacd33ae3d7af76ba8",
      "generation_seconds_batch": 24.629874790087342,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8123250007629395,
        "target_z": 1.1874999598814544,
        "ce": 6.1894097328186035,
        "genuineness": 4.250029563903809,
        "identity": 0.5732560157775879,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était prête, la vieille fenêtre. We've regarded ensemble what it contiens.",
        "wer": 0.42105263157894735,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/100e33bcf8cb00897f1f68bd93e0dd0b0ef87b00fa9029a49fdd93d0b1cfc206.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "1084ff439d6d5392a16b03661166b098977a4065c91f6894d37dbf460e11519e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "674c89624183f045edbf69fafd743840dc500dc80e5836efe6449967a1d934a4",
      "generation_seconds_batch": 18.058475482976064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.284200668334961,
        "target_z": 0.7812501232212469,
        "ce": 6.229123115539551,
        "genuineness": 4.105680465698242,
        "identity": 0.4602976441383362,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1084ff439d6d5392a16b03661166b098977a4065c91f6894d37dbf460e11519e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "10ce13132800ea1a34f0a04df12e0d31c822fedbfedf54b9460f6f0af2270566",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "0d14c0cef38a8f93bca69c8d6300eed4fcd9734e1ad43057b96e6caaac33aa20",
      "generation_seconds_batch": 26.280428793048486,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4263877868652344,
        "target_z": 0.8906249240613247,
        "ce": 6.332377910614014,
        "genuineness": 3.9676074981689453,
        "identity": 0.5055738091468811,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/10ce13132800ea1a34f0a04df12e0d31c822fedbfedf54b9460f6f0af2270566.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "112871f78548f7a79942e3d615c046785d623fc28d91617960a7279471aa1933",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "236e54581e7cbe0d741784247d568c7699b54152e26fbc3e2e10fd29ce0d9e4e",
      "generation_seconds_batch": 24.571042870054953,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2609591484069824,
        "target_z": -0.005859416730451333,
        "ce": 6.348263263702393,
        "genuineness": 4.068024158477783,
        "identity": 0.40414509177207947,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinkommen.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/112871f78548f7a79942e3d615c046785d623fc28d91617960a7279471aa1933.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "119c2874c1b63ee1fb28bd148987416cff6d331da1cd8fb7694026ef2c4613ae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "10e30143a5be4fcae26a368c6a8bc02c17f0b790db6657639bd6e885f5f2814a",
      "generation_seconds_batch": 23.574403621954843,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.348263263702393,
        "genuineness": 4.406930446624756,
        "identity": 0.6902490258216858,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/119c2874c1b63ee1fb28bd148987416cff6d331da1cd8fb7694026ef2c4613ae.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "11b7ac6290cd7f53132f25342cd8dfb29baf82586f3b51c1fb40d77d2dc61a63",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "874dd9595b687745a76f29bfa4401049f36c46e1cefa95f93c99ce6ce5b78844",
      "generation_seconds_batch": 23.385041343979537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.847482204437256,
        "target_z": 0.44531255373019485,
        "ce": 6.229123115539551,
        "genuineness": 4.369274139404297,
        "identity": 0.6762605905532837,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in keren.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/11b7ac6290cd7f53132f25342cd8dfb29baf82586f3b51c1fb40d77d2dc61a63.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "11d7d1ec56ae1395b540ae8a9738d646d53dca09ad0104b406d2b1017a6c0b49",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d0bb6b2448b6322980dabb0ade0c65ee3a294dc75f0f984152422fb03bd41ac3",
      "generation_seconds_batch": 23.944076128071174,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7103729248046875,
        "target_z": 0.3398437861783312,
        "ce": 6.356205940246582,
        "genuineness": 4.419482707977295,
        "identity": 0.5314207077026367,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/11d7d1ec56ae1395b540ae8a9738d646d53dca09ad0104b406d2b1017a6c0b49.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "11f20e977e5551a0b5ee25762d394241766108f738b7ba89cda492054c946416",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f08dc1d580e735b870d28f536570d63ee6ec9bacfd33c7502f7cb750eaa31d9e",
      "generation_seconds_batch": 19.020171663956717,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2943568229675293,
        "target_z": 0.7890625565958053,
        "ce": 6.4912309646606445,
        "genuineness": 4.011539936065674,
        "identity": 0.44014838337898254,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/11f20e977e5551a0b5ee25762d394241766108f738b7ba89cda492054c946416.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "11fda5a763db487c58b22a3a16632856dda91f646d503c89db7ed3e86050edc9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "98eb207c04e603faa0c203a4eaff2588844d6f14e231406c46ed7a43f3fb5264",
      "generation_seconds_batch": 23.133388219051994,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0404505729675293,
        "target_z": 0.5937498882411947,
        "ce": 6.268836498260498,
        "genuineness": 4.419482707977295,
        "identity": 0.32380211353302,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/11fda5a763db487c58b22a3a16632856dda91f646d503c89db7ed3e86050edc9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "12494ee4c10628bccb0b8e678afda40205686c6bbee5d742cd44e33e72fcda7c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "ef11a5c7c81fd53fac8321973c458d3830c8c084c22cf62695640517ed276ea1",
      "generation_seconds_batch": 25.100550384027883,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7607643604278564,
        "target_z": -0.39062496991109086,
        "ce": 6.443574905395508,
        "genuineness": 4.293961524963379,
        "identity": 0.5725690126419067,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/12494ee4c10628bccb0b8e678afda40205686c6bbee5d742cd44e33e72fcda7c.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3eaf7fffcb9db03cf5af4a2932165364f6e98f9478bba691c07d18d1339643e4",
      "generation_seconds_batch": 18.355023359996267,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0514867305755615,
        "target_z": -0.16699218472393992,
        "ce": 6.181467056274414,
        "genuineness": 4.356721878051758,
        "identity": 0.7840725183486938,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "138fa65259405802fa4f282021009c539cb49b5220036479a2d49371a41893da",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "2c45c6306bf21c377794ebe8ca52f63079fe23ea5c2eb519c5273c0d8fa34ddb",
      "generation_seconds_batch": 18.75116862100549,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.555490255355835,
        "target_z": 0.22070316852145783,
        "ce": 6.006728172302246,
        "genuineness": 4.093128204345703,
        "identity": 0.2712152600288391,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/138fa65259405802fa4f282021009c539cb49b5220036479a2d49371a41893da.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "13b7d68e50f267fb59d6cf9ad08456314a8ff4507ce22169167237bb101d731f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d685cee7559cbf82623e9c50a8d7074c05353563ce8741dec2381a021702a96f",
      "generation_seconds_batch": 23.87702177593019,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.005293846130371,
        "target_z": 1.3359376611905847,
        "ce": 6.133810997009277,
        "genuineness": 4.193545341491699,
        "identity": 0.5670027732849121,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/13b7d68e50f267fb59d6cf9ad08456314a8ff4507ce22169167237bb101d731f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "144a5ec997961ff2dc6dae856bcd70253ece2d2718f331a035a6bcd6f38a2dff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a4df56c35fef516184fa694fa5a8205292ecba73d67d83b4d9fdae444ecc483c",
      "generation_seconds_batch": 23.05446971289348,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 6.300607204437256,
        "genuineness": 4.444586753845215,
        "identity": 0.5736513137817383,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/144a5ec997961ff2dc6dae856bcd70253ece2d2718f331a035a6bcd6f38a2dff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "148ba816037a96923e003d34aca2dfbc227ba2cea48c8ec49249e5fd5481b386",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cd1306e1d14c8dfab4684ebc29b00dc1688dfc93e14ea1d5edee94a0d50f9c32",
      "generation_seconds_batch": 18.12649925297592,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.491623878479004,
        "target_z": -0.597656288327539,
        "ce": 6.41180419921875,
        "genuineness": 3.9801597595214844,
        "identity": 0.4164596199989319,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/148ba816037a96923e003d34aca2dfbc227ba2cea48c8ec49249e5fd5481b386.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "14ae5338bf31a39c0b703d27370341719f6e88a841c2e5795b937d56fe21b88b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d8d4ab182fc5235e9b8e12cb72ab7c1b0aa43b7456abf002ba155927fa53defe",
      "generation_seconds_batch": 19.339650981943123,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 6.268836498260498,
        "genuineness": 4.093128204345703,
        "identity": 0.6356335282325745,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/14ae5338bf31a39c0b703d27370341719f6e88a841c2e5795b937d56fe21b88b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "15243518926a246cd12b84b1173866fc64f8f6faa280dc334941f6536bbc690a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "47a33847bc82adafd7a3c32149e09c94fd61f99fbf4e3d500e40109b3d7967e8",
      "generation_seconds_batch": 22.177096643019468,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.48263692855835,
        "target_z": 1.70312496417987,
        "ce": 6.046441555023193,
        "genuineness": 4.030367851257324,
        "identity": 0.5090138912200928,
        "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/15243518926a246cd12b84b1173866fc64f8f6faa280dc334941f6536bbc690a.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a322cfcbc28695a6868e73e8edf5af3aaea9319a5fba8bb5179c7c648a75b73c",
      "generation_seconds_batch": 18.10326093295589,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4814677238464355,
        "target_z": -0.6054687217020974,
        "ce": 6.3641486167907715,
        "genuineness": 4.13078498840332,
        "identity": 0.59638512134552,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zum kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.09523809523809523,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "15af0108dd5480200e654ff8ef62bd36476743f5c9dca33269453d52e8184c7f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1f7bee3fea23018860471fbbdbbdb0356df5467800dd938044a9a638f1b2172e",
      "generation_seconds_batch": 27.420456782914698,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.959200859069824,
        "target_z": 0.5312500544465975,
        "ce": 6.268836498260498,
        "genuineness": 4.444586753845215,
        "identity": 0.7180474996566772,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/15af0108dd5480200e654ff8ef62bd36476743f5c9dca33269453d52e8184c7f.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "161d4161b0d816e3672d71f0fbcfe16e3012ebf9a5b8bf0906b9b3f5995edbf5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5998188f91bd847bf4da070301b4c0bb5b6d57598590466c94627fed28a1f0e9",
      "generation_seconds_batch": 16.118326456053182,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8699438571929932,
        "target_z": -0.30664066923786043,
        "ce": 6.260893821716309,
        "genuineness": 4.425758361816406,
        "identity": 0.6565974950790405,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/161d4161b0d816e3672d71f0fbcfe16e3012ebf9a5b8bf0906b9b3f5995edbf5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "16bd57ff50864c62bafa4607234635642e640419a47bc9408c660af4e24898c7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "03e455210aa5eb310e1b2b5e003d446cd676c645d1983883324732bf28569f75",
      "generation_seconds_batch": 23.831902164965868,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.441622257232666,
        "target_z": 0.9023437575222273,
        "ce": 6.205295085906982,
        "genuineness": 4.306513786315918,
        "identity": 0.5669106841087341,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/16bd57ff50864c62bafa4607234635642e640419a47bc9408c660af4e24898c7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "16f596bc3df711a803b4f01486ecc601f03024335fbc748fc82f679d9bb9f74f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2942fd6b59089b01987d0e43e93cf18543787b43e67cf27841e4d67836f7d978",
      "generation_seconds_batch": 24.424419428920373,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.360762119293213,
        "target_z": 1.6093750300889091,
        "ce": 5.967014789581299,
        "genuineness": 4.13078498840332,
        "identity": 0.5182775259017944,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/16f596bc3df711a803b4f01486ecc601f03024335fbc748fc82f679d9bb9f74f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "17e24471ae5750f23dcbd5b28b27f34f3f9149bc9826486aab5379fcbab019b1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4a7a2e58078ba3906ce97c54c9aedecb98aab4ce533ae4523fabf250fae35258",
      "generation_seconds_batch": 24.9069007729413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.504709005355835,
        "target_z": 0.18164063485053572,
        "ce": 6.221180438995361,
        "genuineness": 4.030367851257324,
        "identity": 0.2643554210662842,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/17e24471ae5750f23dcbd5b28b27f34f3f9149bc9826486aab5379fcbab019b1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "18809cd15b7350de570a4c186e4a5e794e094bd6b5fcf6f72b68f580b4604f12",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e9b2637fa7f63c464ce75dd9d74693b4d7b6bce28ae73be418712dd99ea7edde",
      "generation_seconds_batch": 18.432599129038863,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.365450382232666,
        "target_z": 0.8437499570158441,
        "ce": 6.0146708488464355,
        "genuineness": 4.017816066741943,
        "identity": 0.5357427000999451,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/18809cd15b7350de570a4c186e4a5e794e094bd6b5fcf6f72b68f580b4604f12.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "18fdff09a2eaf157f40065470bf9fa9e5ddbd87ba637102dbcf49e46a821c0c4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e71bc9aed1744258049c1b673173c3394aaa90a8b9448b26fb12822d3c49a092",
      "generation_seconds_batch": 25.93738785700407,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.566915988922119,
        "target_z": 0.22949220191760228,
        "ce": 6.284721851348877,
        "genuineness": 4.061748504638672,
        "identity": 0.5292081832885742,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/18fdff09a2eaf157f40065470bf9fa9e5ddbd87ba637102dbcf49e46a821c0c4.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "1908ecb45272e4475a5da7d942e07e8eeb29615aeba9f7c44e4bbd92409321ef",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1e01f2c5e1a00ea16019fdf4fcab5051f145e71a4f62fc5f91708f3008445233",
      "generation_seconds_batch": 16.501043304917403,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9388883113861084,
        "target_z": 0.5156250042984156,
        "ce": 6.109982967376709,
        "genuineness": 4.2374773025512695,
        "identity": 0.6219233870506287,
        "hypothesis": "J'ai cru le numéro sur l'enveloppe. Lille and verify the two dernier chiffres. Appelle-moi quand tu aurais aimé.",
        "wer": 0.5454545454545454,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1908ecb45272e4475a5da7d942e07e8eeb29615aeba9f7c44e4bbd92409321ef.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "196cf300520bb078b493edc1f377caa4ed2db5b96d66a470cd327cf892a13cff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e2a36795752d4c5bad8872a366c98a3647ee1d4bea7a732a2e27fccc8e298cfb",
      "generation_seconds_batch": 22.72094012994785,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2435755729675293,
        "target_z": 0.7500000229248831,
        "ce": 5.974957466125488,
        "genuineness": 4.143336772918701,
        "identity": 0.6181968450546265,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/196cf300520bb078b493edc1f377caa4ed2db5b96d66a470cd327cf892a13cff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "19e205962a82ac96815be31a83e82ef47d41630757edd3d0e55a4d94090c7ad2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "0a1bc091778ccf31d3bf2e1012e8ff11f7922e69471801bb9c7a60b844a5a612",
      "generation_seconds_batch": 24.255415681982413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.233419418334961,
        "target_z": 0.7421875895503247,
        "ce": 6.348263263702393,
        "genuineness": 4.017816066741943,
        "identity": 0.4407777786254883,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/19e205962a82ac96815be31a83e82ef47d41630757edd3d0e55a4d94090c7ad2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "1a11f3a7b773766e2dec4b95099590e149060858fc3f30ecca0eb3f9926d6564",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fc7cac16153ef7de205be78de6f30e128531f84b552c4ccdc80025ba5745992b",
      "generation_seconds_batch": 17.641377189895138,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6718971729278564,
        "target_z": -0.45898440383520456,
        "ce": 6.38003396987915,
        "genuineness": 4.118232727050781,
        "identity": 0.46445512771606445,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1a11f3a7b773766e2dec4b95099590e149060858fc3f30ecca0eb3f9926d6564.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "1a2c353f965cd3862de8665ffcb316cae617109374efe0871207c60e1e659233",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "68e60a38d5a82446c8d4c69aaad7df9da0519eb601eeb2734d877c27489a121c",
      "generation_seconds_batch": 17.470073992968537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.157247543334961,
        "target_z": 0.6835937890439416,
        "ce": 6.078212261199951,
        "genuineness": 4.093128204345703,
        "identity": 0.7106001377105713,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1a2c353f965cd3862de8665ffcb316cae617109374efe0871207c60e1e659233.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "1a88b2533d5fae4294f33f783eac873af8a14756578d7eba41f0618745ea0bc6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c953352c6517a89c1d91698c18acb9c32f32d6ce8ba0d11021e7530702f06c01",
      "generation_seconds_batch": 16.994527050992474,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7052948474884033,
        "target_z": 0.335937569491052,
        "ce": 6.308549880981445,
        "genuineness": 4.432034492492676,
        "identity": 0.5474340915679932,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1a88b2533d5fae4294f33f783eac873af8a14756578d7eba41f0618745ea0bc6.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "1b21a73fd35432a8a89396d2c181b5d2b20b789553e5794b8f5ac601cebffd23",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9b7b338015f39d6ce86a35e5b2e16407a44f06d4d9118c9cc72fe5a942e80297",
      "generation_seconds_batch": 16.501043304917403,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5381064414978027,
        "target_z": 0.9765624247777273,
        "ce": 6.157639026641846,
        "genuineness": 4.369274139404297,
        "identity": 0.6359584331512451,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1b21a73fd35432a8a89396d2c181b5d2b20b789553e5794b8f5ac601cebffd23.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "1b60f471763142c4eecdc0be8759429b1473d40d84fbcbc747d2b110269151d7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6f2acad7b7944d2519fa9907097e9ae2660ea41069f0f780456d3e748b0e75b5",
      "generation_seconds_batch": 24.014875861932524,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0959203243255615,
        "target_z": -0.1328124677618831,
        "ce": 6.09409761428833,
        "genuineness": 4.281409740447998,
        "identity": 0.6111505031585693,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1b60f471763142c4eecdc0be8759429b1473d40d84fbcbc747d2b110269151d7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "1ba9c7bab9ff56da7cb878226163a5e102c2c2439f74b421fb66e5228714afa3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "aae89647053554f63df563a069813d61c2d402f1cac14b1a1f318552289d709c",
      "generation_seconds_batch": 23.62180249299854,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9388883113861084,
        "target_z": 0.5156250042984156,
        "ce": 6.268836498260498,
        "genuineness": 4.319066047668457,
        "identity": 0.5641709566116333,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1ba9c7bab9ff56da7cb878226163a5e102c2c2439f74b421fb66e5228714afa3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "1be59564116f80809aa9f4682bf108cc3a126aef96bab715fa14b537eacdc77f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2ef531e46997df6f1ba36069497b4536ab0e6db7ce0459617d1e29e62e4fcc18",
      "generation_seconds_batch": 24.541802480001934,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.82716965675354,
        "target_z": 0.42968750358201296,
        "ce": 6.173524379730225,
        "genuineness": 4.306513786315918,
        "identity": 0.7028636932373047,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1be59564116f80809aa9f4682bf108cc3a126aef96bab715fa14b537eacdc77f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "1bf876bad7abef6adaad94cbcf31a895b8dbbc9e0e45389a5f0519c2929d950b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ff6ad0db2d848286c0047b984b011d14d5c609aa0fb50a9b034f4d1210e03635",
      "generation_seconds_batch": 24.013965774909593,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4818575382232666,
        "target_z": 0.16406256805824682,
        "ce": 6.284721851348877,
        "genuineness": 4.017816066741943,
        "identity": 0.246412992477417,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1bf876bad7abef6adaad94cbcf31a895b8dbbc9e0e45389a5f0519c2929d950b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "1c8a96fa3f628f4d72d4358cf3ac41352e1fcff3029d37732afc156b2dbfa937",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0a4b88b0154565ca0499acc02a4d21929e5f7ca9b5f77e3d2a69c42624ce2b80",
      "generation_seconds_batch": 23.820414545945823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.822091579437256,
        "target_z": 0.4257812868947338,
        "ce": 5.911416053771973,
        "genuineness": 4.218649387359619,
        "identity": 0.571797251701355,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1c8a96fa3f628f4d72d4358cf3ac41352e1fcff3029d37732afc156b2dbfa937.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "1d2b7819580d7b076f91232b3ce1c9dc1b57fe145d23544948e69b06c623f617",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "439a3c50dae6bbea2380356d4a572ef51dd2c1fa935ec3dd6cd10a2ef60eb5a9",
      "generation_seconds_batch": 18.694358405075036,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5279502868652344,
        "target_z": 0.9687499914031689,
        "ce": 5.927301406860352,
        "genuineness": 3.823258876800537,
        "identity": 0.4714275598526001,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1d2b7819580d7b076f91232b3ce1c9dc1b57fe145d23544948e69b06c623f617.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91949733d394270980b6e0d8d4a9061cac5f79f36747d3ae53ed311f7b0f459a",
      "generation_seconds_batch": 18.527512040920556,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9232641458511353,
        "target_z": -0.2656250272232987,
        "ce": 6.23706579208374,
        "genuineness": 4.18099308013916,
        "identity": 0.6447266340255737,
        "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f2a91cd9ddd3d974a89ffba9d92fed5dac5f86a6461ec4c311662c87bf8b9f3c",
      "generation_seconds_batch": 16.539653074927628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9753148555755615,
        "target_z": -0.22558598523032308,
        "ce": 6.427689552307129,
        "genuineness": 4.356721878051758,
        "identity": 0.6057459115982056,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "1da993523ae117e2334c9e0c9cb949f42f55e5f544aaf55ae136fffaacebe383",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "762cb8ad17f260d672f2e287ba9aff3fe9c0b61f6a87967b3ba09fc71148c4c4",
      "generation_seconds_batch": 24.444322044961154,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8631062507629395,
        "target_z": 1.2265624935523767,
        "ce": 6.268836498260498,
        "genuineness": 4.268857479095459,
        "identity": 0.2712312340736389,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1da993523ae117e2334c9e0c9cb949f42f55e5f544aaf55ae136fffaacebe383.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "1df2857e7c3b166cb72d975d449c5064f226dc89f471c4888d58f5dcb65510ee",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b868ed2d647c687ae2375b949ce806f2a8498e4f19f5ab2eddc03101f2c0903e",
      "generation_seconds_batch": 25.999391563935205,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.228731155395508,
        "target_z": 1.5078126626233896,
        "ce": 5.895530700683594,
        "genuineness": 3.8922953605651855,
        "identity": 0.5047740936279297,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1df2857e7c3b166cb72d975d449c5064f226dc89f471c4888d58f5dcb65510ee.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "1e36ac5625896414fac88431fb1bfc12669de72e215f0b7d9b5a5cf63fa70133",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a1204368247e309f1a94cbef756089c43fc69182bd45dc8ebf43d713e3e9868a",
      "generation_seconds_batch": 24.444322044961154,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.700606346130371,
        "target_z": 1.101562459165052,
        "ce": 6.1894097328186035,
        "genuineness": 4.231201171875,
        "identity": 0.4073549807071686,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together,",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1e36ac5625896414fac88431fb1bfc12669de72e215f0b7d9b5a5cf63fa70133.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "1e4c19ca73a25178bd03812c57f3d3f930815853f486a8393afd7104398c08eb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5746521f3c77b511c780c445b7c38df9ddc60146482970b50615b4ddd8f12e09",
      "generation_seconds_batch": 24.79015061701648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.309980869293213,
        "target_z": 1.570312496417987,
        "ce": 6.165581703186035,
        "genuineness": 4.193545341491699,
        "identity": 0.39717698097229004,
        "hypothesis": "De nu ook af bij die dijken. Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in.",
        "wer": 0.4444444444444444,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1e4c19ca73a25178bd03812c57f3d3f930815853f486a8393afd7104398c08eb.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "1e626a3061556e8bcfeb0fd459cfd999c2bd4e92c54190e24d89cea13a2ccaaa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0261be54cdfb7b00dd0a04cbb83bc12b29af8387bd9a916b0d7773603143f828",
      "generation_seconds_batch": 16.519894335069694,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.743380546569824,
        "target_z": 0.3652342863451785,
        "ce": 6.403861999511719,
        "genuineness": 4.356721878051758,
        "identity": 0.698613703250885,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1e626a3061556e8bcfeb0fd459cfd999c2bd4e92c54190e24d89cea13a2ccaaa.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Escribí el número en el sobre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "060162f40878b4191f3f0ccccaf1a13649638f5c121e09da33a272549ef63076",
      "generation_seconds_batch": 18.527512040920556,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.238107681274414,
        "target_z": -0.023437483522740245,
        "ce": 6.348263263702393,
        "genuineness": 4.482243061065674,
        "identity": 0.7357006072998047,
        "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "1f16e2d7f9e717905b4e65ea0fe46ce3d738f90bc5bb136f30aa382e993d1884",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e0c3b5f977f06055d84b51cded882399de34ec68df47f5e0b8e0c6e28b2c83de",
      "generation_seconds_batch": 24.496363488957286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4314661026000977,
        "target_z": 0.8945313241476689,
        "ce": 5.974957466125488,
        "genuineness": 4.061748504638672,
        "identity": 0.20428282022476196,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/1f16e2d7f9e717905b4e65ea0fe46ce3d738f90bc5bb136f30aa382e993d1884.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "204106041aa2f6717e56d24704a8909f2c8de07908195e9a39b4c92d612b8138",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "5d0b8987d3f415f7ecc955774c67d3ddf61ff884ea43ce03fc169169823a3d14",
      "generation_seconds_batch": 24.721887089894153,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2537317276000977,
        "target_z": 0.7578124562994415,
        "ce": 6.3641486167907715,
        "genuineness": 3.8295347690582275,
        "identity": 0.2919192910194397,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/204106041aa2f6717e56d24704a8909f2c8de07908195e9a39b4c92d612b8138.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "20c910d27272ca3da9b0e2e2d2b5c321b157871a6fe1374f361979fd3186a254",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5d73bd0e97869a89d465b37609f96b58c8b02afaa874983acf653ee60cac37e9",
      "generation_seconds_batch": 17.50111776497215,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2537317276000977,
        "target_z": 0.7578124562994415,
        "ce": 6.340320587158203,
        "genuineness": 4.105680465698242,
        "identity": 0.4578726291656494,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/20c910d27272ca3da9b0e2e2d2b5c321b157871a6fe1374f361979fd3186a254.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "20d64847e32fab322e5bab3dde7a912d30cc60786f867fc9ec1ac29617e0cad0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8c3c31d8595368502d392b199945bedde91d838115e6be9ca1a9e8bdad6f8a2c",
      "generation_seconds_batch": 25.04858072393108,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.167793273925781,
        "target_z": 1.460937328779779,
        "ce": 6.165581703186035,
        "genuineness": 3.6851859092712402,
        "identity": 0.33495253324508667,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/20d64847e32fab322e5bab3dde7a912d30cc60786f867fc9ec1ac29617e0cad0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "20f303c8d53e4502c4020eb9b0f6576338f45cc485c6791ab1d19532313a3686",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8b493a59216dcb4cfab781779ae1a27fa09fc1eb0bd8dc52d9ceb68b92d7daf4",
      "generation_seconds_batch": 24.692658704007044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8427939414978027,
        "target_z": 1.21093762680326,
        "ce": 6.0305562019348145,
        "genuineness": 4.017816066741943,
        "identity": 0.6036465167999268,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/20f303c8d53e4502c4020eb9b0f6576338f45cc485c6791ab1d19532313a3686.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "210bf7b74477d8dfa9c4726ea9f4f3b53a5ec35fe766127f808c67e9b2817980",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "872d7a52a305643ee903cf62219c3c66a629d52b9410d0fbe5b68b11b3f39cf9",
      "generation_seconds_batch": 16.557607111055404,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5643768310546875,
        "target_z": 0.22753900187443016,
        "ce": 6.252951145172119,
        "genuineness": 4.174716949462891,
        "identity": 0.6354812383651733,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/210bf7b74477d8dfa9c4726ea9f4f3b53a5ec35fe766127f808c67e9b2817980.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "2204a1983dcd0166beab4c0f111b23116037ba865a8a04bf4c607175fcdc8b33",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "16ad9d66de1ed2c19c911ad1340c15e76da25b34986f23e05a37879865979466",
      "generation_seconds_batch": 24.3141505359672,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.117925643920898,
        "genuineness": 3.440420389175415,
        "identity": 0.3448143005371094,
        "hypothesis": "The door is still open. I put your code on the chair. Tell me when you are ready.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2204a1983dcd0166beab4c0f111b23116037ba865a8a04bf4c607175fcdc8b33.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "229601c64a311cb65bfa0ba9fe38c49cb11a559b6ac84e504358394c1af32bc0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "216886cdeb256b94fae82340fd32a902bf2e34ba790ae83788183b500c1f900b",
      "generation_seconds_batch": 24.43482965999283,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.141753673553467,
        "genuineness": 3.848362922668457,
        "identity": 0.6107349395751953,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/229601c64a311cb65bfa0ba9fe38c49cb11a559b6ac84e504358394c1af32bc0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "2366eaf9955219be98405014c4563b3de502a97b85689a8c4f207a755f747912",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e3852eedb7a69549958d939816915b27f254c7063524fde1544ed6e1ef34ee80",
      "generation_seconds_batch": 24.907184681040235,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7179901599884033,
        "target_z": 0.34570320290878254,
        "ce": 6.3641486167907715,
        "genuineness": 4.645420074462891,
        "identity": 0.5659939646720886,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2366eaf9955219be98405014c4563b3de502a97b85689a8c4f207a755f747912.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "23acafaad63724d943235a84edb071631fd4789b306668c2c08298907ea7b8a6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bca9d8dfde4b715558414313bbf5232894ab660b3b487ab9d575db92a724d693",
      "generation_seconds_batch": 24.0803997219773,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.768771171569824,
        "target_z": 0.38476555318063954,
        "ce": 6.181467056274414,
        "genuineness": 4.256305694580078,
        "identity": 0.4616531729698181,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/23acafaad63724d943235a84edb071631fd4789b306668c2c08298907ea7b8a6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "241cd995b0c824237e65a8df536c0934e647619e324e41af09126bff17db9c7d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "29bc70cd8ade092eeff1618d3fd9e89ef2b757bf96a7abad45ddb3d8d889f04a",
      "generation_seconds_batch": 24.180515447980724,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.934199810028076,
        "target_z": 1.2812498939724155,
        "ce": 6.133810997009277,
        "genuineness": 4.256305694580078,
        "identity": 0.6941404342651367,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/241cd995b0c824237e65a8df536c0934e647619e324e41af09126bff17db9c7d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "247698ef059ed9814143c993c49d22d93976e5e996098ede3214b40a984e56c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "a840576af3b070ecf8a3a4f54726e064cbf743dbf563055b7a7b4654d884b580",
      "generation_seconds_batch": 22.37469820503611,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6092002391815186,
        "target_z": 1.0312500085968312,
        "ce": 5.498397350311279,
        "genuineness": 3.452972412109375,
        "identity": 0.33379942178726196,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás limpiendo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/247698ef059ed9814143c993c49d22d93976e5e996098ede3214b40a984e56c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "24a5c1a297d579ac1546432467454485e7f802257bfe7a6ff71e5af17278684d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4f992b5607344647d2fbafb5acdc5d69a9263ac83a2b7c02594f43d21f563715",
      "generation_seconds_batch": 23.326820596004836,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9138875007629395,
        "target_z": 1.2656250272232987,
        "ce": 5.6254801750183105,
        "genuineness": 4.068024158477783,
        "identity": 0.41918444633483887,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/24a5c1a297d579ac1546432467454485e7f802257bfe7a6ff71e5af17278684d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "24e6ae370a4d2f034b3a28f55cb8a859ebd33502640c1cdc7df9df035a0ccbe5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fd8651feb253c954f7b20ca2677a84a0b849f6915e7354df1306ac99bdea8964",
      "generation_seconds_batch": 18.51648142898921,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.182638168334961,
        "target_z": 0.7031250558794027,
        "ce": 6.205295085906982,
        "genuineness": 4.3127899169921875,
        "identity": 0.7030357122421265,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/24e6ae370a4d2f034b3a28f55cb8a859ebd33502640c1cdc7df9df035a0ccbe5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "24f0f894c9fc67165861a5d8ec0a8a6bb3ec14bc8b41419dce2658897aa598a8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1f22be6bbc2be15777e096543d700fffdbd0ee0fc2317c55e5d5446a73e52fb1",
      "generation_seconds_batch": 23.82025758700911,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0844945907592773,
        "target_z": -0.14160150115802755,
        "ce": 6.467403411865234,
        "genuineness": 4.024092197418213,
        "identity": 0.3680570125579834,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/24f0f894c9fc67165861a5d8ec0a8a6bb3ec14bc8b41419dce2658897aa598a8.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "25407fc50be7a3a72dda6597593a41adb1ffda6f0b6712f64a3661c1d941f384",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ba78257422982c80dc717ba1bd84de12595b72c1b04f5e20e732d5b93c642dae",
      "generation_seconds_batch": 16.65904374793172,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.606271505355835,
        "target_z": 0.25976570219237993,
        "ce": 6.229123115539551,
        "genuineness": 4.080576419830322,
        "identity": 0.6298147439956665,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/25407fc50be7a3a72dda6597593a41adb1ffda6f0b6712f64a3661c1d941f384.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "256abaa3eabb2b627ec457a90bd2aa0276aad547909d4a8babc7ec98a53cd006",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b609e6776d8b0e37efded9b10460150854fa475d256c95928c5916b0f20d8b39",
      "generation_seconds_batch": 24.33617350202985,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0966997146606445,
        "target_z": 1.4062499283597403,
        "ce": 6.1020402908325195,
        "genuineness": 3.961331605911255,
        "identity": 0.4475556015968323,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/256abaa3eabb2b627ec457a90bd2aa0276aad547909d4a8babc7ec98a53cd006.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "25a470518493003f94e96805ffffc3e5098acf2d91afd189bdf1b19801e4f204",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "205f262a7ea8eacc0ea153a4c315b5dba3e1b1ceda9afeffbc7f06f6e19e963f",
      "generation_seconds_batch": 17.641377189895138,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9803930521011353,
        "target_z": -0.22167967684351136,
        "ce": 6.332377910614014,
        "genuineness": 4.262581825256348,
        "identity": 0.580237627029419,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/25a470518493003f94e96805ffffc3e5098acf2d91afd189bdf1b19801e4f204.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "261fa9e49e17c5cdbd5ee7a805a2abd9903845d7d4eb3a4c3d2fca1f486926f1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "761596b0ef4bc446c822f5a457c4a439ac4ae1004a557f5644409980d9a2e6f6",
      "generation_seconds_batch": 24.23462665406987,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.365450382232666,
        "target_z": 0.8437499570158441,
        "ce": 6.125868320465088,
        "genuineness": 3.6914620399475098,
        "identity": 0.4212013781070709,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/261fa9e49e17c5cdbd5ee7a805a2abd9903845d7d4eb3a4c3d2fca1f486926f1.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "263f39574ab88d7261bed6320d2660c975f723d567ec10f75ea1185ed3938787",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4820f673664aee692a10eecc819679461019153999b3627ac72de614af5e656c",
      "generation_seconds_batch": 16.507789566065185,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4713114500045776,
        "target_z": -0.6132812467761883,
        "ce": 6.221180438995361,
        "genuineness": 3.9801597595214844,
        "identity": 0.5736131072044373,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.045454545454545456,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/263f39574ab88d7261bed6320d2660c975f723d567ec10f75ea1185ed3938787.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "2676d832b92fe801952db878585b82f20ac7f6c0537b6a044d0661a4a2d77a32",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4590cd643148378fb4310aecaa6d3e46f0485e77e51c55547bd0e7587f9a165a",
      "generation_seconds_batch": 22.96646749402862,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.055685043334961,
        "target_z": 0.6054687217020974,
        "ce": 6.165581703186035,
        "genuineness": 4.18099308013916,
        "identity": 0.5299712419509888,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2676d832b92fe801952db878585b82f20ac7f6c0537b6a044d0661a4a2d77a32.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "26919be56297e2bdf3b9775154e859fe542d47b888c890d5095f2a7938c73990",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "45df7261f4591c1c304a214f28e27abaea0cf1e3d0b37eaf1fa443954f49d562",
      "generation_seconds_batch": 19.060352484928444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 6.054384231567383,
        "genuineness": 3.848362922668457,
        "identity": 0.2765149772167206,
        "hypothesis": "Tretür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/26919be56297e2bdf3b9775154e859fe542d47b888c890d5095f2a7938c73990.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "6bebb233644fbbae614c671b1e67f7b3f97bd1c6f8324298b53b574cfa55cdd3",
      "generation_seconds_batch": 17.605224541039206,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0375218391418457,
        "target_z": -0.17773441816325652,
        "ce": 6.403861999511719,
        "genuineness": 4.469690799713135,
        "identity": 0.3053327798843384,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "26d9e2dea10f99a59e70dc4d10a25208f9072886235767b665d0ac65ae97191d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "85318b26624ea8522f9dae1f3acfeabd1c716961dab1f98435518212bd41917b",
      "generation_seconds_batch": 18.47205436602235,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2787325382232666,
        "target_z": 0.007812433374558387,
        "ce": 5.998785495758057,
        "genuineness": 4.362998008728027,
        "identity": 0.6140294075012207,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/26d9e2dea10f99a59e70dc4d10a25208f9072886235767b665d0ac65ae97191d.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "26ec7b99b7bc3afd039dab6732f40e3efdc8a136d939a72bc75a700c35031240",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "26148520bbd7169082bd224cc6d0968da01320917176ec2c4ab8fcd250f8231c",
      "generation_seconds_batch": 16.548658450017683,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.649435520172119,
        "target_z": 0.2929688191328507,
        "ce": 6.157639026641846,
        "genuineness": 4.168440818786621,
        "identity": 0.763182520866394,
        "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/26ec7b99b7bc3afd039dab6732f40e3efdc8a136d939a72bc75a700c35031240.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "276be1332e81748128028be2339aca793c75cfda93ed0e08740fc7c84f6dc3d5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "cfc2864d963e4e552ea457d48ecbc881a007fa6eb8dd365f15955f82ffa725b7",
      "generation_seconds_batch": 16.584737755008973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.244455337524414,
        "target_z": -0.018554666813874982,
        "ce": 6.221180438995361,
        "genuineness": 4.344170093536377,
        "identity": 0.6366808414459229,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/276be1332e81748128028be2339aca793c75cfda93ed0e08740fc7c84f6dc3d5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "27e9ddd28fa69467fac9fb684ab38d7c5f3f22e26f53567d31f550d3b9b1a065",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "60464ddc3cdd8e309476266a95cb7f10c668ca2935554e91e636d6c079f4e31c",
      "generation_seconds_batch": 24.413228293065913,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.111544370651245,
        "target_z": 0.6484374720602987,
        "ce": 5.486483573913574,
        "genuineness": 4.099404335021973,
        "identity": 0.2515653967857361,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/27e9ddd28fa69467fac9fb684ab38d7c5f3f22e26f53567d31f550d3b9b1a065.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "27f985053da2f3c3521c4dc6a5ff14c5ac2b04533a7638a59ddd4ad985901b52",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8a63e0ca1c41f85e770c95e4b47ba7bc498ae10ef2005eb3ccdc7fc3ffd7ebb0",
      "generation_seconds_batch": 23.980190902017057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.43185567855835,
        "target_z": 1.664062430508948,
        "ce": 5.816103935241699,
        "genuineness": 3.873466968536377,
        "identity": 0.6001169085502625,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/27f985053da2f3c3521c4dc6a5ff14c5ac2b04533a7638a59ddd4ad985901b52.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "28225ae6740636bb7d8264c3e22e05d8906cc182e31ae5c6975e8bec3e926a40",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "602faac194b615e17ed8557c760485b06ec7b8d7fab24b94c5166589fd1b6bd2",
      "generation_seconds_batch": 24.180515447980724,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.923654079437256,
        "target_z": 0.503906354236578,
        "ce": 6.205295085906982,
        "genuineness": 4.432034492492676,
        "identity": 0.7743086814880371,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/28225ae6740636bb7d8264c3e22e05d8906cc182e31ae5c6975e8bec3e926a40.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "28a14d0fcb8b6f8be884f4f1c513158f37aebe8d26321c0496dbe77d3ae37fc3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "61607724651b93f3b248735ba8a78b5a3084e522bf65becff9f8c8afbb4e25ac",
      "generation_seconds_batch": 23.944076128071174,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 6.4515180587768555,
        "genuineness": 4.337893962860107,
        "identity": 0.5805000066757202,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/28a14d0fcb8b6f8be884f4f1c513158f37aebe8d26321c0496dbe77d3ae37fc3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "28cd11d3d65258cb3ec98fd2028d74f6c1cdbb7c8ddc4e161b40d1d7805b101d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "0c1ece19c02bedbec9b727ae51b3ddc2a06bfa2245c6e2a911364c0130713875",
      "generation_seconds_batch": 17.272471650969237,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 5.486483573913574,
        "genuineness": 4.1998209953308105,
        "identity": 0.17746993899345398,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaagt.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/28cd11d3d65258cb3ec98fd2028d74f6c1cdbb7c8ddc4e161b40d1d7805b101d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "2913ab4b26ec54d10da739529ec917fd7005d30c2163a3ffc38e5421bfb258be",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8cfa203d4448fba66ce129134cefdc4aa0c8e1c40a8fa75ee62c2801fc883953",
      "generation_seconds_batch": 25.201634799013846,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.420285224914551,
        "target_z": 0.11669920930244074,
        "ce": 6.3641486167907715,
        "genuineness": 4.444586753845215,
        "identity": 0.6353063583374023,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2913ab4b26ec54d10da739529ec917fd7005d30c2163a3ffc38e5421bfb258be.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "2948f16aa06927a53d1fd7beeb9b7e41c8586e86972f4cbf507d6050d52881c3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "3302928304aac8d730ee8a3c4a7874f20171ed165ca5de2a009281e0c13dd910",
      "generation_seconds_batch": 24.667846460011788,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.543574333190918,
        "target_z": 1.7499999312253507,
        "ce": 6.022613525390625,
        "genuineness": 4.243753433227539,
        "identity": 0.49269548058509827,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2948f16aa06927a53d1fd7beeb9b7e41c8586e86972f4cbf507d6050d52881c3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "29d81c7ee0dab2912acb5a198929b38c77f1bbfe2482f99bd1ccb3a58a533c77",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "abb1d426b5a859fcb169014cc4d31cd08a6d73e8b8d36186cf420c01b4ab1d82",
      "generation_seconds_batch": 24.486056388006546,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.832247734069824,
        "target_z": 0.43359372026929216,
        "ce": 6.24500846862793,
        "genuineness": 4.093128204345703,
        "identity": 0.5072660446166992,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/29d81c7ee0dab2912acb5a198929b38c77f1bbfe2482f99bd1ccb3a58a533c77.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "29dd98565ba51017688d6468445bcb1f414297b990d069c5ab90b357fc6a594a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "7f84257adc42c869e51352dafae673c9dbb149cb8c000243148d57d662569bb8",
      "generation_seconds_batch": 21.02395355689805,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.334981679916382,
        "target_z": 0.8203124734931039,
        "ce": 6.125868320465088,
        "genuineness": 4.457139015197754,
        "identity": 0.6194034814834595,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/29dd98565ba51017688d6468445bcb1f414297b990d069c5ab90b357fc6a594a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "29ed0c244f92e0b41e966d3b9a2d28662e4faa3e613d8732d1ed286f8e1b983a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "1fa521385d4a7c469b10cc20b9b7551ab01330d99c96d90d6b9515966acb6948",
      "generation_seconds_batch": 17.331806177971885,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 6.252951145172119,
        "genuineness": 4.400654315948486,
        "identity": 0.6434863805770874,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/29ed0c244f92e0b41e966d3b9a2d28662e4faa3e613d8732d1ed286f8e1b983a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "2a07f18b44914d3f12007cfab04bc9c9b87004414c56fbcccfdff6bbd72671f0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "36b8310e22f9841dde83188a310baaa894a7840c99192eb9d5b54ae3cd5ec281",
      "generation_seconds_batch": 26.185742670088075,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5381064414978027,
        "target_z": 0.9765624247777273,
        "ce": 6.133810997009277,
        "genuineness": 4.061748504638672,
        "identity": 0.4779048562049866,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2a07f18b44914d3f12007cfab04bc9c9b87004414c56fbcccfdff6bbd72671f0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "2a34ef246ff4c156ca189703d6571388a35cb335392f377ab55fbb20d8fc552d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9f351886a437a7e8528c10b6da3b59b07c578b93d067b302f519a74c2d248f1b",
      "generation_seconds_batch": 19.060352484928444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.720918893814087,
        "target_z": 1.1171875093132337,
        "ce": 6.205295085906982,
        "genuineness": 4.168440818786621,
        "identity": 0.5139804482460022,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2a34ef246ff4c156ca189703d6571388a35cb335392f377ab55fbb20d8fc552d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "2a906512611090bdbc36f8846dbb98f4df85e196b643ed3524f1653620fae7ff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "f8b2ab5abd53024360ede0f40966f2c66850a88909c9898f5a2cfe5f849f80b7",
      "generation_seconds_batch": 25.047236039070413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 5.720792293548584,
        "genuineness": 3.4969046115875244,
        "identity": 0.26338833570480347,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás limpiando.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2a906512611090bdbc36f8846dbb98f4df85e196b643ed3524f1653620fae7ff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "2a9166481dea0f4d2043f58566916ae8849633df7c0b25043c682ad947400732",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "848b5c82d68fcca2149436cdc77d83623a246e128a6662d587ff4442519515e8",
      "generation_seconds_batch": 23.79733815405052,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 6.308549880981445,
        "genuineness": 3.9299514293670654,
        "identity": 0.5131531953811646,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2a9166481dea0f4d2043f58566916ae8849633df7c0b25043c682ad947400732.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "2accf5d6cdd934ad004f2087e8e97de689a19fc5705ad617c267a7aed3e94a3a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6c3ef35fad499e4dfa7871d409758292049fdb3689971f8f98671ae95c1956d4",
      "generation_seconds_batch": 24.425652467063628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.314669132232666,
        "target_z": 0.804687423344922,
        "ce": 6.1894097328186035,
        "genuineness": 4.193545341491699,
        "identity": 0.2945653796195984,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2accf5d6cdd934ad004f2087e8e97de689a19fc5705ad617c267a7aed3e94a3a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "2ad7cc85262727af3a8e30445eb45ca1b22a27df30dd8a056ea6dbc8b329d010",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "55b6963677d85304916baec759d27e48048b3df741d3ea62b38792f55054065d",
      "generation_seconds_batch": 16.688994994037785,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4640841484069824,
        "target_z": 0.15039071795323708,
        "ce": 6.483288764953613,
        "genuineness": 4.21237325668335,
        "identity": 0.4646683633327484,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2ad7cc85262727af3a8e30445eb45ca1b22a27df30dd8a056ea6dbc8b329d010.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "2ae1124e02b9558d72e4383649cb9a202e61f3fa72851c34823360457e112838",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0f41a84e171d679d5d7cff96ee8a45335413d0786db8381fa3dd879ac08e0712",
      "generation_seconds_batch": 27.420456782914698,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.512326240539551,
        "target_z": 0.18750005158098706,
        "ce": 6.252951145172119,
        "genuineness": 4.137060642242432,
        "identity": 0.6316375732421875,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2ae1124e02b9558d72e4383649cb9a202e61f3fa72851c34823360457e112838.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "2aef9784dee3b8243b3cc903e4dc59591bdb1164fda2296406aa9820298b6b8e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2d30cf6650ac4f26b927d6e72b810aa91b58ceb868df512f7f2fcfcb181e0341",
      "generation_seconds_batch": 16.626545223989524,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.474240303039551,
        "target_z": 0.15820315132779547,
        "ce": 6.062326908111572,
        "genuineness": 4.005263805389404,
        "identity": 0.6935831308364868,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2aef9784dee3b8243b3cc903e4dc59591bdb1164fda2296406aa9820298b6b8e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "2b44ff992cd8e43b972f092ae729f7661db47a16e6d12b496b7786a969c77c92",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "57246cc41c99d3cb8ac93babd7f87308cfae63a5d44d915d916566e34cce108b",
      "generation_seconds_batch": 19.65502963704057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.308549880981445,
        "genuineness": 3.9425034523010254,
        "identity": 0.6086525917053223,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2b44ff992cd8e43b972f092ae729f7661db47a16e6d12b496b7786a969c77c92.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "2ba0d3f7c4830e2f80638b7831dc511bc26331e90258a45e8156dee070f35652",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6828c8443e6fc4e6c86877636c931fbd4601d410afd7452b4ed41d72e5bb145",
      "generation_seconds_batch": 18.48575787700247,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6820534467697144,
        "target_z": -0.45117187876111364,
        "ce": 6.38003396987915,
        "genuineness": 4.080576419830322,
        "identity": 0.33586370944976807,
        "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2ba0d3f7c4830e2f80638b7831dc511bc26331e90258a45e8156dee070f35652.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "2bf083ad47dd7c780131a35dd299f0c7a0da53fa5829f3b12f7e286b9e21f614",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e92e0861acb4a5511a24de9f9b24bb95f750dc71912bb5047e9eecc39f6c3886",
      "generation_seconds_batch": 16.45483191299718,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9490444660186768,
        "target_z": 0.523437437672974,
        "ce": 6.1020402908325195,
        "genuineness": 4.20609712600708,
        "identity": 0.6218168139457703,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2bf083ad47dd7c780131a35dd299f0c7a0da53fa5829f3b12f7e286b9e21f614.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "2cc02f871aa964ed5f1fa61df5cf06b93259ad4d70851fd20f138f4d6663712c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8d56ad4da8782d11a207198dda8c5ca6abe7e13158d6bd64f3ee8b2ddee9e6a2",
      "generation_seconds_batch": 22.44229081296362,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.974824905395508,
        "target_z": 1.3124999942687792,
        "ce": 6.205295085906982,
        "genuineness": 4.20609712600708,
        "identity": 0.5530567765235901,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2cc02f871aa964ed5f1fa61df5cf06b93259ad4d70851fd20f138f4d6663712c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "2ce5e3676d9ff808e30413ff760ca7c2ad8890b21514e19c0df0d6d7eda50810",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 131,
      "seconds_generated": 10.48,
      "mp3_sha256": "8faed96b9237d211851022165037f300c9a9a70ec425c48ae7b772bd524f329f",
      "generation_seconds_batch": 25.54227895499207,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.086543560028076,
        "target_z": 1.3984374949851819,
        "ce": 5.5738525390625,
        "genuineness": 3.452972412109375,
        "identity": 0.302227646112442,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abriendo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.28000000000000114,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2ce5e3676d9ff808e30413ff760ca7c2ad8890b21514e19c0df0d6d7eda50810.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "2d2191ad46fb3ba3f34c9463cbbd7b8426dd25a066de92c5f9582cfc47a3869a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2cba75a130b73050954e31dc809ef88a6c4d17a683a011bf5824f05eda513714",
      "generation_seconds_batch": 15.690243636025116,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.3595927953720093,
        "target_z": -0.6992187474925909,
        "ce": 6.443574905395508,
        "genuineness": 4.15588903427124,
        "identity": 0.2629530131816864,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2d2191ad46fb3ba3f34c9463cbbd7b8426dd25a066de92c5f9582cfc47a3869a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "2de579ad67fc61063c5dc8dd582c41fb1123c6984e066fcd40c1b491bdd436ac",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "1d2179d3d709c2a2958cbad73b981d75bd14946a97b5a52490072a3e04b89878",
      "generation_seconds_batch": 17.816202211077325,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.954512596130371,
        "target_z": 1.2968751275196624,
        "ce": 6.133810997009277,
        "genuineness": 4.168440818786621,
        "identity": 0.44609689712524414,
        "hypothesis": "En que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hace.",
        "wer": 0.23529411764705882,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2de579ad67fc61063c5dc8dd582c41fb1123c6984e066fcd40c1b491bdd436ac.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "2ed20456f2bea5c7e5f73f753364d1f173279276d5bd2424c34de43cc5c41977",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e46c332fd1f998bcd53985793b0d146c46e903cec470c1f5d70ead20bdce1f6b",
      "generation_seconds_batch": 24.74157860199921,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.787323951721191,
        "target_z": 1.9374997994072725,
        "ce": 5.677107334136963,
        "genuineness": 4.099404335021973,
        "identity": 0.39391618967056274,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2ed20456f2bea5c7e5f73f753364d1f173279276d5bd2424c34de43cc5c41977.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "2f0e42b638dddd2166142b369b0cd5a138314a5bf140d32555f40073d346ea24",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ee7f6967b746dc90389a0f4506a1a1ae934c7fa4b1345a2891a5ec1a0f33cead",
      "generation_seconds_batch": 23.821577762020752,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8373258113861084,
        "target_z": 0.43749993695657136,
        "ce": 6.300607204437256,
        "genuineness": 4.457139015197754,
        "identity": 0.5259971022605896,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2f0e42b638dddd2166142b369b0cd5a138314a5bf140d32555f40073d346ea24.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "2f11199ba80af4b2454199be686805443da6d4ec5389ee15b755a807915ad67c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "ca92466da611d3d1bfbc11ee87baba6e6709df1e3e03df5ca969b533ef0424e8",
      "generation_seconds_batch": 24.430934706004336,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.18224835395813,
        "target_z": -0.06640623388094155,
        "ce": 6.38003396987915,
        "genuineness": 3.8922953605651855,
        "identity": 0.16172462701797485,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/2f11199ba80af4b2454199be686805443da6d4ec5389ee15b755a807915ad67c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "3043a947d4714a4404958558b29b5b030f13fb3eaee5cb36ff59dc6407225f28",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "223f313b43a209636fcdea45ab89330bd682b85895f35b495576620a9d864fa3",
      "generation_seconds_batch": 24.73492790898308,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.010861873626709,
        "target_z": -0.19824210162123856,
        "ce": 6.300607204437256,
        "genuineness": 4.005263805389404,
        "identity": 0.30394184589385986,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3043a947d4714a4404958558b29b5b030f13fb3eaee5cb36ff59dc6407225f28.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "3073b804c5ffff171ddd94fa1bbfee3405247320367ee89df2b504e05e60b43b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d99a554d97bbe98e8b9c6af1d438ca9a3776e01f3d61885d5072fbb25e9a3d36",
      "generation_seconds_batch": 23.82025758700911,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2304904460906982,
        "target_z": -0.02929690025319158,
        "ce": 6.395919322967529,
        "genuineness": 4.055472373962402,
        "identity": 0.5118072032928467,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3073b804c5ffff171ddd94fa1bbfee3405247320367ee89df2b504e05e60b43b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "309a8141e34d6f80621022b2fbd9c12f798d6a1c1ec88dc437f94c1259c1b11f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "599f02df978b2a7a936cbf7c3e730ce37fb0a6eb57bc8a82184840ee56ee5541",
      "generation_seconds_batch": 19.8482762289932,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.0305562019348145,
        "genuineness": 3.7542223930358887,
        "identity": 0.2613292932510376,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/309a8141e34d6f80621022b2fbd9c12f798d6a1c1ec88dc437f94c1259c1b11f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "30a23e49a2f0c468a92b1ac8469e319a4199bf74e142b435718813c99e4b8b22",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e09cb0b951f378fc910dd8c38d454bbb0f00b5e1a9d72056d5a03fed2cc227ab",
      "generation_seconds_batch": 24.0803997219773,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.162325620651245,
        "target_z": 0.6875000057312208,
        "ce": 6.268836498260498,
        "genuineness": 4.494794845581055,
        "identity": 0.691799521446228,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/30a23e49a2f0c468a92b1ac8469e319a4199bf74e142b435718813c99e4b8b22.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "31593399a8658b6e85d4fc921bd75150345bd70ee59cf247daa09271ed540f25",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0ccdcb7ef81fac6237cc14d72a3c307f2484b2801a4f3b0fb399120024c94d08",
      "generation_seconds_batch": 23.326820596004836,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 5.808161735534668,
        "genuineness": 3.9927117824554443,
        "identity": -0.03600459545850754,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/31593399a8658b6e85d4fc921bd75150345bd70ee59cf247daa09271ed540f25.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "31ae163a08941ae5342249ade6731854843ec8f4c9a5175aad1321526c481cbb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "76b075a6a9e8da55329200ae2c6fc02aab4ac9736924ca349dafc437d50f4da1",
      "generation_seconds_batch": 17.323144803056493,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5787315368652344,
        "target_z": 1.007812525074091,
        "ce": 6.006728172302246,
        "genuineness": 4.143336772918701,
        "identity": 0.5997588634490967,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/31ae163a08941ae5342249ade6731854843ec8f4c9a5175aad1321526c481cbb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "31df0374251d2200ddba9571ad4c0be0512c4603a2d26c03433dae4e55aeab8c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6e4929e3a606998866a93f9fe7bb327ba3b56dc9a85a7514bf1c25d7b9745726",
      "generation_seconds_batch": 21.99821150198113,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.954122543334961,
        "target_z": 0.5273436543602532,
        "ce": 6.165581703186035,
        "genuineness": 4.143336772918701,
        "identity": 0.6151477098464966,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/31df0374251d2200ddba9571ad4c0be0512c4603a2d26c03433dae4e55aeab8c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "31e36d5f10c12e255ee6d46cbdba4dc1ac8b687769dfcebd8d4549e9acb6d4f6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0ff468e37201f00151596e5a2a8a03563c573528c56959825acfa1d04e18b864",
      "generation_seconds_batch": 22.061856417101808,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1009984016418457,
        "target_z": -0.1289062510746039,
        "ce": 6.38003396987915,
        "genuineness": 3.8797430992126465,
        "identity": 0.5204576253890991,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/31e36d5f10c12e255ee6d46cbdba4dc1ac8b687769dfcebd8d4549e9acb6d4f6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "322ca1f56d578428cf7aca226068b20ab01d981da8246aa01a567167a8012f43",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "aafe93b14f981ff651fffaaa2a7213130903d568c4d2317937ff09a2a1951ea6",
      "generation_seconds_batch": 24.37468330306001,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7357635498046875,
        "target_z": 0.35937505301379224,
        "ce": 6.086154937744141,
        "genuineness": 4.444586753845215,
        "identity": 0.6381479501724243,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/322ca1f56d578428cf7aca226068b20ab01d981da8246aa01a567167a8012f43.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "32c2509edd8a1fb6c47ac8ce9d9140cebddeddb5bc584af787e903c3e25495fe",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7db4e2235ac0a4af9910444af7c36e9730192c355f8668444d640b0cca6836df",
      "generation_seconds_batch": 23.869801393942907,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.259199619293213,
        "target_z": 1.5312499627470648,
        "ce": 6.165581703186035,
        "genuineness": 4.068024158477783,
        "identity": 0.4740051031112671,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/32c2509edd8a1fb6c47ac8ce9d9140cebddeddb5bc584af787e903c3e25495fe.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "332eb8072483e0c52d7fa2db148a178a7dd106e023a5f8b7f658d6515599f855",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "10c08a4b570f7f962ee08c51bc45e69e2aa644f26426e33cd1e165d8e7917855",
      "generation_seconds_batch": 24.479064603918232,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.504709005355835,
        "target_z": 0.18164063485053572,
        "ce": 6.300607204437256,
        "genuineness": 3.7667744159698486,
        "identity": 0.3421679735183716,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/332eb8072483e0c52d7fa2db148a178a7dd106e023a5f8b7f658d6515599f855.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "336f428e71a53d2d6447a2960a88f8c90cc3e9dd6d2b99a51961e2e3c8353bfc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2022edded22ff6d58bed81265996b238aefd7c08784e48dd7260991e7d56627c",
      "generation_seconds_batch": 23.621111784945242,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 5.112323760986328,
        "target_z": 2.1874998681819218,
        "ce": 6.38003396987915,
        "genuineness": 4.344170093536377,
        "identity": 0.4665030241012573,
        "hypothesis": "Heheh! J'ai trouvé la petite boîte. Elle is près de la vieille fenêtre. We've regarded ensemble what it contained.",
        "wer": 0.42105263157894735,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/336f428e71a53d2d6447a2960a88f8c90cc3e9dd6d2b99a51961e2e3c8353bfc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "339e0b8892ef4ad1b0fd4d0e0ede450dcc1bd29c2ebe7a40ee18adca3cb03f7b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "866700ce24efbaa46ca4b6d38035722cf5724d49d488d1bf478f7206959d51c5",
      "generation_seconds_batch": 19.621911557973363,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3197474479675293,
        "target_z": 0.8085938234312663,
        "ce": 6.260893821716309,
        "genuineness": 4.3881025314331055,
        "identity": 0.49881333112716675,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/339e0b8892ef4ad1b0fd4d0e0ede450dcc1bd29c2ebe7a40ee18adca3cb03f7b.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "33bd5138aae5491d937f8597f943d501a54a032f3b3c383854ec5e5772c4aba5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7cc70d008e6ab0d20c08b04f42984bbdb421819f01c63867b657484c51d327f9",
      "generation_seconds_batch": 19.035375859006308,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.017209529876709,
        "target_z": -0.1933592849123733,
        "ce": 6.356205940246582,
        "genuineness": 3.9299514293670654,
        "identity": 0.2039780467748642,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/33bd5138aae5491d937f8597f943d501a54a032f3b3c383854ec5e5772c4aba5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "33e24c5f66866940cb43bca0dd126a74fea55c8d4fcefcd0a596b6d705ee0a80",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9a7b83ba65db9430d79085041ba113c0116b949fce359893a524f952b0ee79d9",
      "generation_seconds_batch": 25.20912540704012,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0459184646606445,
        "target_z": 1.367187394688818,
        "ce": 6.054384231567383,
        "genuineness": 3.6412534713745117,
        "identity": 0.522193193435669,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/33e24c5f66866940cb43bca0dd126a74fea55c8d4fcefcd0a596b6d705ee0a80.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "33e433daa3263866834699fb91ecd4ced491bd2baca5bcea42ad1651bcf55cd3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "09a580309f338534c5064144415a338999761944d88739a6774948b6cce36e31",
      "generation_seconds_batch": 16.448250198038295,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.77638840675354,
        "target_z": 0.39062496991109086,
        "ce": 6.427689552307129,
        "genuineness": 4.086852550506592,
        "identity": 0.5363056063652039,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zum kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.09523809523809523,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/33e433daa3263866834699fb91ecd4ced491bd2baca5bcea42ad1651bcf55cd3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "33f406224c0b3b84deee7b48db871abffeaef38e38ac8361fb3666307fba44fc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "edf556af156977c8b6661bb43e1406698e5e28a3a46a73315b3a29b748065250",
      "generation_seconds_batch": 26.72081136808265,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2689661979675293,
        "target_z": 0.7695312897603442,
        "ce": 6.181467056274414,
        "genuineness": 3.9299514293670654,
        "identity": 0.320980966091156,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/33f406224c0b3b84deee7b48db871abffeaef38e38ac8361fb3666307fba44fc.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "49f1e539a95208a9b9e797623de3cf53498bb4bb4340aa727898d8e205c0f37d",
      "generation_seconds_batch": 17.905752851977013,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5326385498046875,
        "target_z": 0.20312491833010382,
        "ce": 6.09409761428833,
        "genuineness": 4.394378662109375,
        "identity": 0.7534661293029785,
        "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "341fb64d1d7856b2392b6d64a2ab356526efaba2b6179bdcdae7338a78a20053",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a011405a44f1e0c223c425d8d7b87bb7c830e93d6c458a2d68b1b40cc3d76111",
      "generation_seconds_batch": 16.4739788119914,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0404505729675293,
        "target_z": 0.5937498882411947,
        "ce": 6.205295085906982,
        "genuineness": 4.457139015197754,
        "identity": 0.44559764862060547,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, quand nous pourrons parler?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/341fb64d1d7856b2392b6d64a2ab356526efaba2b6179bdcdae7338a78a20053.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "3422c817a8bd3d72d6f1483052777c94d7617f160ddf0905c79c3d385a983707",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5655f1a19cd355c9368e75e460bb670a1b4f8ee0b1aaccc1278cda4ca2b35b2d",
      "generation_seconds_batch": 24.166113131912425,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.10607647895813,
        "target_z": -0.1250000343873247,
        "ce": 6.086154937744141,
        "genuineness": 3.9550557136535645,
        "identity": 0.2547152042388916,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3422c817a8bd3d72d6f1483052777c94d7617f160ddf0905c79c3d385a983707.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ce4772a214e0a0de76d9a9dd5797d37ba4f9f389eb96aeff9bc53987d8e190e0",
      "generation_seconds_batch": 17.486787848058157,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.1006085872650146,
        "target_z": -0.8984375408349481,
        "ce": 6.4515180587768555,
        "genuineness": 4.105680465698242,
        "identity": 0.3451515734195709,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "34eebc359e510eeedb8890bbccbc397747e3318019e11472c2b83bd6251a23c1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "a80b851b37666a7e266bdea9e8176404beaa57b042769ce67e5a9dffa1cdf4ea",
      "generation_seconds_batch": 17.561124850064516,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.025606155395508,
        "target_z": 1.3515625279397012,
        "ce": 6.332377910614014,
        "genuineness": 4.432034492492676,
        "identity": 0.7607870697975159,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/34eebc359e510eeedb8890bbccbc397747e3318019e11472c2b83bd6251a23c1.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "34ef31cbfc67f20c607de281adb8b7231a684b8f68b8519781e7faa7ff46cff0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6ffb3cd32b44b23e88847994aeadec5fda2df0e2ff5cc9137392c6f38302bd46",
      "generation_seconds_batch": 17.743167817941867,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1657445430755615,
        "target_z": -0.0791014839643652,
        "ce": 6.173524379730225,
        "genuineness": 4.557555198669434,
        "identity": 0.624295711517334,
        "hypothesis": "Ton message est arrivé après mon départ ? Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/34ef31cbfc67f20c607de281adb8b7231a684b8f68b8519781e7faa7ff46cff0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3514b09142da4f925311af9fd6faee2dafe5ab12fd09ba60c426e29229b00396",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "512b0d424123f63689635f18192f196fd01eace555cc000af2ad1c4c43000cca",
      "generation_seconds_batch": 15.782711612991989,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.056075096130371,
        "target_z": 1.3750001948615067,
        "ce": 6.332377910614014,
        "genuineness": 4.256305694580078,
        "identity": 0.6318976283073425,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3514b09142da4f925311af9fd6faee2dafe5ab12fd09ba60c426e29229b00396.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "35645ac586e48ec356ca2adb813424848fd394f4efc0cd3c72df126419193304",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b9e03ed6b81e5c3053c3f02f0a931727451a50445062ce84cdb4ef4651c12f38",
      "generation_seconds_batch": 23.046598840039223,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7408416271209717,
        "target_z": 0.36328126970107144,
        "ce": 6.38003396987915,
        "genuineness": 4.306513786315918,
        "identity": 0.5322666168212891,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/35645ac586e48ec356ca2adb813424848fd394f4efc0cd3c72df126419193304.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "35baad2178da648355af1d51c56a300de1a52fb58768d61bebae00d9286b39b5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "33772f136c3d60527748de1ddf1f569e0662f9352d1416ec6edf11e21a2972e0",
      "generation_seconds_batch": 24.057538067921996,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.959200859069824,
        "target_z": 0.5312500544465975,
        "ce": 6.24500846862793,
        "genuineness": 4.331617832183838,
        "identity": 0.44867873191833496,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/35baad2178da648355af1d51c56a300de1a52fb58768d61bebae00d9286b39b5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "35c6d162f1b83986b2955c665612ce8071a4637a29d71e79958941a38d93a2f3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "59930a60eef2cb29991e767475f71aa8f54f3157ecf3eb5f53391885f5e999ed",
      "generation_seconds_batch": 23.133388219051994,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7916228771209717,
        "target_z": 0.40234380337199355,
        "ce": 6.324435234069824,
        "genuineness": 4.325342178344727,
        "identity": 0.3605765104293823,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/35c6d162f1b83986b2955c665612ce8071a4637a29d71e79958941a38d93a2f3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "36b3bba8b37e574339639a7fc23e6e68b4d1931cb6712597b9ef4cd54066e71d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e4b9e5c52f65166790f0143d3218dbdb7f2ff0bc1c0bae24538994e63d86cfa1",
      "generation_seconds_batch": 24.763327075983398,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.48263692855835,
        "target_z": 1.70312496417987,
        "ce": 5.506340026855469,
        "genuineness": 3.9801597595214844,
        "identity": 0.41247090697288513,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/36b3bba8b37e574339639a7fc23e6e68b4d1931cb6712597b9ef4cd54066e71d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "36c627254c79c9ad68e637e82f8a65d55352e2ea9d787132bcadabace3cb8dd6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dd48c1b6c0bb8f066dad89732184a3942e5a20cf9239066ad4bdac5b497bc99b",
      "generation_seconds_batch": 24.3141505359672,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 5.7128496170043945,
        "genuineness": 3.6412534713745117,
        "identity": 0.4164523482322693,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/36c627254c79c9ad68e637e82f8a65d55352e2ea9d787132bcadabace3cb8dd6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "3710324fb546e2dd7bb7a452dc220467a0192ca64d1cbd354bb299abd3e9d163",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "d315204577eb810f3a078e1cd44f236b7460838e943aece9d216830ca073554e",
      "generation_seconds_batch": 25.00551747600548,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 5.919358730316162,
        "genuineness": 4.061748504638672,
        "identity": 0.5723763704299927,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3710324fb546e2dd7bb7a452dc220467a0192ca64d1cbd354bb299abd3e9d163.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3727cd3265270714c87577ee5ae938ce7ca8cb173f1bf24aff942373eb8c38ec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9d086da20e8e9d057af20abb5d8934594e77301b7ec4b3507578a69b83d7c9c0",
      "generation_seconds_batch": 22.217637603986077,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.877561092376709,
        "target_z": -0.3007812525074091,
        "ce": 6.0305562019348145,
        "genuineness": 4.419482707977295,
        "identity": 0.7094787359237671,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3727cd3265270714c87577ee5ae938ce7ca8cb173f1bf24aff942373eb8c38ec.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "3787595b23d4698ea782a2c8d350400a563eed1416584ce00cb603ac8ca45cd6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9824a722087047dc3b0e656a20a85b34931e8feb227ceb7d7736430233c6ca6d",
      "generation_seconds_batch": 22.177096643019468,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.949824333190918,
        "target_z": 2.0625002005927273,
        "ce": 6.157639026641846,
        "genuineness": 4.2751336097717285,
        "identity": 0.6647340655326843,
        "hypothesis": "I've tried the petite boat. It is pretty fenêtre. We will regard what continues.",
        "wer": 0.8947368421052632,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3787595b23d4698ea782a2c8d350400a563eed1416584ce00cb603ac8ca45cd6.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "379ff21fff91b2f21bf0949b4bafd41d7fef4e77da3975489c6802156895710e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6ab3637df570d7efafa950068841ec55f6222ed9eb9c93f158142af6c0441190",
      "generation_seconds_batch": 16.36648829909973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2089085578918457,
        "target_z": -0.045898367023894424,
        "ce": 6.395919322967529,
        "genuineness": 4.250029563903809,
        "identity": 0.1487802416086197,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/379ff21fff91b2f21bf0949b4bafd41d7fef4e77da3975489c6802156895710e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "38106de7ee2f0e134d68227d98f2a10a8f76aa95a3fbf62de452f5d61b5b0ca0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ed99bd1b5a340cbfe28035d688283e02bd94be20e4168264c4c960bb9309e5f4",
      "generation_seconds_batch": 29.312737667001784,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9443562030792236,
        "target_z": 1.289062510746039,
        "ce": 6.23706579208374,
        "genuineness": 3.898571252822876,
        "identity": 0.5275535583496094,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/38106de7ee2f0e134d68227d98f2a10a8f76aa95a3fbf62de452f5d61b5b0ca0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "381e8d17d23eeebe1ce0d62c6cbc28c63c532c7d95b88bc9db5d3bfe6b139447",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "0206c654684aac4682ec1f3489c8a3246f17b344fe30102a298f7b6dd271e61a",
      "generation_seconds_batch": 25.253876965958625,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.6045122146606445,
        "target_z": 1.7968752650689612,
        "ce": 5.9431867599487305,
        "genuineness": 4.2751336097717285,
        "identity": 0.6033502817153931,
        "hypothesis": "Elle était prêt de la vie fenêtre. Nous pouvons regarder ensemble.",
        "wer": 0.5263157894736842,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/381e8d17d23eeebe1ce0d62c6cbc28c63c532c7d95b88bc9db5d3bfe6b139447.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "384dc3875b993e0ee420a2663388cc7bde9ec65801cae8cdd49530ad73f969f5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6babb63d032b851d3a5c183c926aa244471d32d3be924752c432a67fb65d60f",
      "generation_seconds_batch": 24.426237762905657,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.157639026641846,
        "genuineness": 4.005263805389404,
        "identity": 0.4244316816329956,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/384dc3875b993e0ee420a2663388cc7bde9ec65801cae8cdd49530ad73f969f5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "3874dde79b2d900f819c1622503d929c10dcc7c7d8481344410fee91d958f707",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "848685fd76f759a00a03584ffa54a0f574ec5205563da9527d72c436c96308ea",
      "generation_seconds_batch": 22.44229081296362,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5076379776000977,
        "target_z": 0.9531251246540521,
        "ce": 6.205295085906982,
        "genuineness": 3.9801597595214844,
        "identity": 0.40633726119995117,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3874dde79b2d900f819c1622503d929c10dcc7c7d8481344410fee91d958f707.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "38ae9308dd3d3d91ef647c9c7be6333379b37cecfafac747456dfe93e2284ef6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "edc2cd14be8b71543115ec93809c1501d84754ac43089ffe5d6b06e69d51c858",
      "generation_seconds_batch": 24.669216251000762,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.593576192855835,
        "target_z": 0.2500000687746494,
        "ce": 6.260893821716309,
        "genuineness": 4.419482707977295,
        "identity": 0.5735824108123779,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/38ae9308dd3d3d91ef647c9c7be6333379b37cecfafac747456dfe93e2284ef6.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "393855d0cc9f738e3ed3e0fb788f65a0eb7f1fcb45ed5bdaaac7d35822c550d1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a94d428a1f3b80215e11006b7f6b6f44326cc4d09ad57171720f1c494156216f",
      "generation_seconds_batch": 20.921538257040083,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.182638168334961,
        "target_z": 0.7031250558794027,
        "ce": 6.229123115539551,
        "genuineness": 4.250029563903809,
        "identity": 0.6147722005844116,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/393855d0cc9f738e3ed3e0fb788f65a0eb7f1fcb45ed5bdaaac7d35822c550d1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "399fc70c6e080745dda3fd7abd2c329b0fff7700060d0a821c44edb64b99a100",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "34647b505c9b38ced918b968dd9871b0ced6cc1cbe8a90af2bdbc9c3b700dd4f",
      "generation_seconds_batch": 24.56605463998858,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.517794132232666,
        "target_z": 0.9609375580286105,
        "ce": 6.2767791748046875,
        "genuineness": 4.545003414154053,
        "identity": 0.6866078972816467,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/399fc70c6e080745dda3fd7abd2c329b0fff7700060d0a821c44edb64b99a100.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "39b432321ddce2f199acefb6a1d59033b8fa1db3f40b512d6283b574989cdd25",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "e76345e05229add2a1ee63c04d1e1d511827c959b9cfceb1d8da4772eef70d55",
      "generation_seconds_batch": 26.00134980492294,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 6.046441555023193,
        "genuineness": 4.362998008728027,
        "identity": 0.5250214338302612,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/39b432321ddce2f199acefb6a1d59033b8fa1db3f40b512d6283b574989cdd25.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "39fa92856577e7172c5b3cb76041cf6bff582f79b2ae9f720c87c8393f1156d1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "524453d9facfa4993e074d18ca9d2f238cc7ccc5867590e0d276ba84c57cd81c",
      "generation_seconds_batch": 24.764511785004288,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.5537309646606445,
        "target_z": 1.7578127313980392,
        "ce": 6.300607204437256,
        "genuineness": 4.444586753845215,
        "identity": 0.501052975654602,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/39fa92856577e7172c5b3cb76041cf6bff582f79b2ae9f720c87c8393f1156d1.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "3adc29e267a5bb050b7993b09fa6d217f87502c2d67100fbe89087a47d9256cb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c04f8395e5430a87c6b888fa30b9d64f17708eee2445d2821958f793fdc87ff0",
      "generation_seconds_batch": 16.548781483084895,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.720918893814087,
        "target_z": 1.1171875093132337,
        "ce": 6.221180438995361,
        "genuineness": 4.331617832183838,
        "identity": 0.5227445960044861,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3adc29e267a5bb050b7993b09fa6d217f87502c2d67100fbe89087a47d9256cb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "3ae1be7a4bb27dfe8413a7f341608330b797af658b33eb339a585a6b0883fbbc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "6472220b3df06f04dc83725e274e62e14e45480949cf255c760e0c4b2d9c6885",
      "generation_seconds_batch": 25.267574862926267,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2660372257232666,
        "target_z": -0.00195320004317214,
        "ce": 6.23706579208374,
        "genuineness": 4.432034492492676,
        "identity": 0.6584553122520447,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3ae1be7a4bb27dfe8413a7f341608330b797af658b33eb339a585a6b0883fbbc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "3af3e9d22416407840d11f1413118a4c69245257e89e11e82fb0a6d82d6d5450",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91b99d4c3ef93c0bf23d7b158ca751afe9d441810bba16738807f9c611e17f0e",
      "generation_seconds_batch": 24.14466606604401,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6802940368652344,
        "target_z": 1.0859375924159351,
        "ce": 6.197352409362793,
        "genuineness": 4.256305694580078,
        "identity": 0.6467564105987549,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3af3e9d22416407840d11f1413118a4c69245257e89e11e82fb0a6d82d6d5450.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3b775d1e5bd75dd7a95e841e3e02a02bf943d4059fc87e67c3e914b3de009117",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1500bd7bc149126629121def109b7fd33bcd9df4edb911316f1b7a12f6bd221d",
      "generation_seconds_batch": 23.797777066007257,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7179901599884033,
        "target_z": 0.34570320290878254,
        "ce": 6.213237762451172,
        "genuineness": 4.65797233581543,
        "identity": 0.8125625252723694,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3b775d1e5bd75dd7a95e841e3e02a02bf943d4059fc87e67c3e914b3de009117.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "3bfacabfe276afae71adc9005e3a1a3d70e08327975c616ee232e209be65782c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "acc1ff3695bd36a82fbbde253b65cdd467c40f3f5cd2270e4ffe03c12fb155b0",
      "generation_seconds_batch": 24.128403423936106,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9134976863861084,
        "target_z": 0.49609373746295454,
        "ce": 6.1894097328186035,
        "genuineness": 4.093128204345703,
        "identity": 0.3040138781070709,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3bfacabfe276afae71adc9005e3a1a3d70e08327975c616ee232e209be65782c.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "00bbd1746efd5b54883a7a28a89a8db89ae2e70e78207e809687a3646474026a",
      "generation_seconds_batch": 17.222310820012353,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6465065479278564,
        "target_z": -0.47851567067066564,
        "ce": 6.086154937744141,
        "genuineness": 4.2249250411987305,
        "identity": 0.632347583770752,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "3c9c1fb2e372842e7709ba7eccb195833d45ac7bc0528ead454883a6c3408a21",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b657f8bccc50deedab9547f78955361188b4b2fd706e42645da3fe86672a6660",
      "generation_seconds_batch": 24.523544859024696,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.751387596130371,
        "target_z": 1.140624992835974,
        "ce": 6.1020402908325195,
        "genuineness": 4.256305694580078,
        "identity": 0.6399222612380981,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3c9c1fb2e372842e7709ba7eccb195833d45ac7bc0528ead454883a6c3408a21.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3cb7ec703cb535b0080b2e594a61c3b4eedbc281ce761e255e25340fbaef1fb3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "aaf7136c52e9e894addb855f205dc3d5a895adef4669378f455b6a3220688445",
      "generation_seconds_batch": 24.561673025018536,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6904501914978027,
        "target_z": 1.0937500257904935,
        "ce": 6.229123115539551,
        "genuineness": 4.137060642242432,
        "identity": 0.6526830196380615,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3cb7ec703cb535b0080b2e594a61c3b4eedbc281ce761e255e25340fbaef1fb3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "3d4630e86dfc205d6a2507867e04b7549243a6ed35637ce88c93e7d86766c821",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9c4ae21fc55c19315ea0a7ccf9083ab4566ff9fd93e9952413d223cfc8768fd7",
      "generation_seconds_batch": 24.087617627927102,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6037323474884033,
        "target_z": 0.2578125021492078,
        "ce": 4.722001075744629,
        "genuineness": 3.5094566345214844,
        "identity": 0.1457371860742569,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen.",
        "wer": 0.1111111111111111,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3d4630e86dfc205d6a2507867e04b7549243a6ed35637ce88c93e7d86766c821.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3d7ad52be128f133579ddeae7b6bcf8ef15dd2d7061af86234d641962f24a6c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f95310f8823aff1bd9f8de4fb6ce918c44017cd6eb2264f5d0c56f85291d6c9f",
      "generation_seconds_batch": 17.97813995706383,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.289278507232666,
        "target_z": 0.7851561565094609,
        "ce": 6.252951145172119,
        "genuineness": 4.105680465698242,
        "identity": 0.6109310388565063,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3d7ad52be128f133579ddeae7b6bcf8ef15dd2d7061af86234d641962f24a6c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "3e72b16110673522a70784da6d9327a983b12ef38e7228bc46d96eb01db6edad",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ee999e6e89fff028e1dbc50051a5858f950723d4d5bba933d8ab5b8998961ef4",
      "generation_seconds_batch": 23.261828650953248,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7920126914978027,
        "target_z": 1.1718750931323378,
        "ce": 6.062326908111572,
        "genuineness": 4.068024158477783,
        "identity": 0.5941232442855835,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3e72b16110673522a70784da6d9327a983b12ef38e7228bc46d96eb01db6edad.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "3eac8b1a0b61739da59565c5cdf35a99d89971035eee33af646c27f8c7d4b0bc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "39c732380ab0c4df0ce7fae7aec01e1c80df6329dc9f98bed75f3c0d0eb93ab4",
      "generation_seconds_batch": 17.913794555002823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4873251914978027,
        "target_z": 0.9374998911068051,
        "ce": 6.213237762451172,
        "genuineness": 4.419482707977295,
        "identity": 0.21440404653549194,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3eac8b1a0b61739da59565c5cdf35a99d89971035eee33af646c27f8c7d4b0bc.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "3f38c251a7572e4ed2d67f7fe248333c150513e85b7eeaf1cef677e503077c9a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9d36889fc1b2f686ee0fda5cd3af1f8e0b377aa4090e11be65f32efa3544c433",
      "generation_seconds_batch": 18.555340529885143,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9816625118255615,
        "target_z": -0.22070316852145783,
        "ce": 6.221180438995361,
        "genuineness": 4.406930446624756,
        "identity": 0.5363365411758423,
        "hypothesis": "¿Alguien ha movido la pequeña silla azul? Estaba aquí, junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3f38c251a7572e4ed2d67f7fe248333c150513e85b7eeaf1cef677e503077c9a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "3f73c8f36c3e993a37fe4594f1ebc0e9f60a9d1f690aff63982249ff6a668a43",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4a2dd315027fb5a679ce22e921a5c605da46083911f790eae6bf2d27669ceacc",
      "generation_seconds_batch": 23.67438012198545,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.006728172302246,
        "genuineness": 4.3127899169921875,
        "identity": 0.39317798614501953,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3f73c8f36c3e993a37fe4594f1ebc0e9f60a9d1f690aff63982249ff6a668a43.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "3fc237841bc90ef1ac4e666666e3f943ba73f1bb937f74360638d53cda25805f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "9ecda86995c5b33e744cb1bc25316120b25626a6b6d8fb412ee163cbbe51cc7e",
      "generation_seconds_batch": 21.152613825979643,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9951374530792236,
        "target_z": 1.328125044416961,
        "ce": 6.038498878479004,
        "genuineness": 4.143336772918701,
        "identity": 0.5287237763404846,
        "hypothesis": "I've tried the petite boîte. Elle is pretty fenêtre. We've regarded what.",
        "wer": 0.7894736842105263,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/3fc237841bc90ef1ac4e666666e3f943ba73f1bb937f74360638d53cda25805f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "401a2ad7c95b3097a8c5c22e5007150873ea44b9322a2aefe842649755f8ae09",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6463bc0fb90cad0b0170361e40b9e00859d60b358ba8793bf1a8a707d36c1064",
      "generation_seconds_batch": 24.411455484922044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0459184646606445,
        "target_z": 1.367187394688818,
        "ce": 5.95112943649292,
        "genuineness": 4.356721878051758,
        "identity": 0.19714447855949402,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/401a2ad7c95b3097a8c5c22e5007150873ea44b9322a2aefe842649755f8ae09.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "403256ecc0088995872bba67ec470acdb4d764b1e19d9e4e85234e7d5b67d6c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5e39712191ffc49b515f1ce5c472223f1e83283983e935d37b77fe080516969b",
      "generation_seconds_batch": 18.423131512012333,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 6.125868320465088,
        "genuineness": 4.545003414154053,
        "identity": 0.6099507808685303,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/403256ecc0088995872bba67ec470acdb4d764b1e19d9e4e85234e7d5b67d6c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "40a1b6011fbacc5479e23c2fe73b97b9936578a6ffe1ca2f63850e72227bbe98",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e3070713115833cc09db26f0381c9a970f1f388897a9aa090d7d9de7b5eb15bf",
      "generation_seconds_batch": 16.911234361934476,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6295127868652344,
        "target_z": 1.046875058745013,
        "ce": 6.109982967376709,
        "genuineness": 4.20609712600708,
        "identity": 0.5695266723632812,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/40a1b6011fbacc5479e23c2fe73b97b9936578a6ffe1ca2f63850e72227bbe98.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "410419c81679451242c2c3ffbdad4c8717be64fe5e90bb86fedcbc2b543973f5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dcb9ec2c350c3a9119d9accc0b810cd085445432fc3ce1b7c290fafb8d4ac5da",
      "generation_seconds_batch": 17.66493027098477,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5076379776000977,
        "target_z": 0.9531251246540521,
        "ce": 6.252951145172119,
        "genuineness": 3.440420389175415,
        "identity": 0.3027699589729309,
        "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/410419c81679451242c2c3ffbdad4c8717be64fe5e90bb86fedcbc2b543973f5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "410cc258916190ec02efe9f96c1e045124a2df3e73062a71b434dce943b09b94",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9e774f72cff12392d23253799c78c1a219db51249fe1c03bb46a691655f9ead9",
      "generation_seconds_batch": 24.058952579973266,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2537317276000977,
        "target_z": 0.7578124562994415,
        "ce": 6.3641486167907715,
        "genuineness": 4.118232727050781,
        "identity": 0.4109715223312378,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/410cc258916190ec02efe9f96c1e045124a2df3e73062a71b434dce943b09b94.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "43247aad01f9ac50a99f58801b69bf3f38e4c2842a3a7a72eb8547dc28448eaf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "87e179598ae4e39e101c284020776262e68aef4ca52b7335c1ab3cd0ffe6dfd9",
      "generation_seconds_batch": 16.727655808092095,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7818562984466553,
        "target_z": 1.1640624763587142,
        "ce": 6.109982967376709,
        "genuineness": 4.268857479095459,
        "identity": 0.4793880879878998,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/43247aad01f9ac50a99f58801b69bf3f38e4c2842a3a7a72eb8547dc28448eaf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "434427d4857dd2ad162dc17678dfd3acdbaaab458c6e1e926256608af05e2439",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ad89f52ed8d231b2b77242d8ab3c2cab4bfc376aa2b86e47027753694c62126e",
      "generation_seconds_batch": 25.203110423055477,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 6.157639026641846,
        "genuineness": 4.3504462242126465,
        "identity": 0.6077547669410706,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/434427d4857dd2ad162dc17678dfd3acdbaaab458c6e1e926256608af05e2439.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "427d981904cac43dc63145f0d2adefd051451826e3db507c4b2ee3975b68de4a",
      "generation_seconds_batch": 17.905752851977013,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7230682373046875,
        "target_z": 0.34960941959606173,
        "ce": 6.109982967376709,
        "genuineness": 4.457139015197754,
        "identity": 0.5900649428367615,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "43a8caa8e8ceef299e6581bbccec53d5f3bdd235f3e18887e6037c3458361e85",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3c1594f9a36286e0ea58745565aa7b9be9c731746b74dc6d31db9c5b3e816365",
      "generation_seconds_batch": 19.65502963704057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.340449333190918,
        "target_z": 1.5937497965416623,
        "ce": 6.133810997009277,
        "genuineness": 3.9048471450805664,
        "identity": 0.45629292726516724,
        "hypothesis": "I found a little box. It was beside the old window. We can look inside together.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/43a8caa8e8ceef299e6581bbccec53d5f3bdd235f3e18887e6037c3458361e85.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "43c8ddef49a43d6c2d5f13f7d443d05d8b76ed6779e91c56b19b276956347c76",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d29e8b961969ce7acdc1973cd4f0ec41d77df5424e5d2a5d3bf700e984a7e453",
      "generation_seconds_batch": 17.79419536900241,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1724817752838135,
        "target_z": 0.6953124391057792,
        "ce": 6.133810997009277,
        "genuineness": 4.168440818786621,
        "identity": 0.5604402422904968,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/43c8ddef49a43d6c2d5f13f7d443d05d8b76ed6779e91c56b19b276956347c76.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "43cc285c1c4aae93f2239dcf9de42441fbd0905a6d6847271853695d627578a4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e03330ad7fff7d1fa355c3a8cfe9436d5c397c0e2e8acc64e9a1daa1617e7553",
      "generation_seconds_batch": 22.72521257097833,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.492793083190918,
        "target_z": 1.7109373975544284,
        "ce": 5.95112943649292,
        "genuineness": 4.168440818786621,
        "identity": 0.5197408199310303,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/43cc285c1c4aae93f2239dcf9de42441fbd0905a6d6847271853695d627578a4.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8bdd1617b764108992ff22fd628177b3c3febe48a7badc4a2a55acd8fe9342bb",
      "generation_seconds_batch": 19.093078062986024,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7759987115859985,
        "target_z": -0.37890622814972075,
        "ce": 6.181467056274414,
        "genuineness": 4.18099308013916,
        "identity": 0.5989848375320435,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "440bdc40253f21cea8b34f0359f85e425a2fcf6e1cd38ba8c7830e6a95b0d790",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2ccbfe7c9822eca039981b310995ef99dadf64b7b39a5ef38653c1d49c60f148",
      "generation_seconds_batch": 24.919410910923034,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 5.685050010681152,
        "genuineness": 3.6412534713745117,
        "identity": 0.25634151697158813,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/440bdc40253f21cea8b34f0359f85e425a2fcf6e1cd38ba8c7830e6a95b0d790.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "4433f964517eb7f78e104a305363a2d7c93ddd7f03e981b868df41d88499cb0a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "133860fc44601c661bde878937c799d24ff93d80c717919088b08b1441dfd701",
      "generation_seconds_batch": 17.574932757066563,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.340939521789551,
        "target_z": 0.05566400044162495,
        "ce": 6.165581703186035,
        "genuineness": 4.2374773025512695,
        "identity": 0.554258406162262,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4433f964517eb7f78e104a305363a2d7c93ddd7f03e981b868df41d88499cb0a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "445d119ea0143bf106450443e0338d56632977c3efdb24ff9ecaa992045a6f55",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6e9b7aa9ea4df13a0d5cc3831627db56d20069662e6db5e2ccee9c6c980f43cd",
      "generation_seconds_batch": 25.201634799013846,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6849822998046875,
        "target_z": 0.32031251934287014,
        "ce": 6.197352409362793,
        "genuineness": 4.400654315948486,
        "identity": 0.6611539125442505,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/445d119ea0143bf106450443e0338d56632977c3efdb24ff9ecaa992045a6f55.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "446b08ad2474a6cce823110e6f2563cca6c8a8da53b0e77538d84262fac0ccab",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "184c047a736f41ceae694789b6643a63a8748c5d240c194358164ad78b9b1105",
      "generation_seconds_batch": 25.039864843012765,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.563886642456055,
        "target_z": 1.7656247979744675,
        "ce": 6.125868320465088,
        "genuineness": 4.061748504638672,
        "identity": 0.5476304292678833,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.",
        "wer": 0.3684210526315789,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/446b08ad2474a6cce823110e6f2563cca6c8a8da53b0e77538d84262fac0ccab.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "44722909db101647725f3bad3ab8edd15833621985a898f01e6d090541efb68a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "689c5d5a10d28a647e696a20c879cf81caf4fb249df809c777fd884eca3c4595",
      "generation_seconds_batch": 24.394059024984017,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5584189891815186,
        "target_z": 0.9921874749259091,
        "ce": 6.268836498260498,
        "genuineness": 4.432034492492676,
        "identity": 0.737952709197998,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/44722909db101647725f3bad3ab8edd15833621985a898f01e6d090541efb68a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "447b2d474b121cc6feea3fca154d21bdfaca747e62570e095dfcebac8d9d1ee6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d5959208d161cd38bb421ae681b7cbbdaced17c4adeddc08dd35212813cf6a4f",
      "generation_seconds_batch": 25.015094945090823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.09338116645813,
        "target_z": -0.13476566780505522,
        "ce": 6.070269584655762,
        "genuineness": 4.381826400756836,
        "identity": 0.6256340742111206,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/447b2d474b121cc6feea3fca154d21bdfaca747e62570e095dfcebac8d9d1ee6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "4513441f210886d2e37bc4c7f6cc8a405eabdc258285ae469763b0829a4c8eee",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b907e7073496398a5a01311ceb0611868ee70067857c8c2befa62b2a86667401",
      "generation_seconds_batch": 25.012409711955115,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7107625007629395,
        "target_z": 1.1093748925396103,
        "ce": 6.252951145172119,
        "genuineness": 4.419482707977295,
        "identity": 0.5009603500366211,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4513441f210886d2e37bc4c7f6cc8a405eabdc258285ae469763b0829a4c8eee.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "4546d62beb510f884627244e3ebafc39136277a7984bb663fd923d66eb619242",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91e70d393c1f870681953a537e44d9d39973b534d521f29582012f84deaeb6ec",
      "generation_seconds_batch": 23.124252639943734,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1420130729675293,
        "target_z": 0.6718749555830389,
        "ce": 6.4515180587768555,
        "genuineness": 4.507347106933594,
        "identity": 0.4178796410560608,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4546d62beb510f884627244e3ebafc39136277a7984bb663fd923d66eb619242.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "458c7b3cf0e5db0b818c94640ace847cb838800cef13c431778329b00d9cf842",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c60c026718f3e98385e2f9038119401bf14b15ff60f757547950c013113f8727",
      "generation_seconds_batch": 19.161313239019364,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4691622257232666,
        "target_z": 0.15429693464051628,
        "ce": 6.125868320465088,
        "genuineness": 4.061748504638672,
        "identity": 0.6337536573410034,
        "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/458c7b3cf0e5db0b818c94640ace847cb838800cef13c431778329b00d9cf842.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "459b034ee9125e878c8c0cd50116a13ce642ec9dd983607da7c64635f634fde4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6578df90e501ca90302bb12fca988269323d8f261af13e574f833d1a8a8fb4b9",
      "generation_seconds_batch": 17.016234740032814,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.959200859069824,
        "target_z": 0.5312500544465975,
        "ce": 6.213237762451172,
        "genuineness": 4.256305694580078,
        "identity": 0.7273417115211487,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/459b034ee9125e878c8c0cd50116a13ce642ec9dd983607da7c64635f634fde4.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e9d4896bb5be7402392704945135e655c0b88f2f798cca25c5d292e3552b19e5",
      "generation_seconds_batch": 17.954962073010392,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.1006085872650146,
        "target_z": -0.8984375408349481,
        "ce": 6.308549880981445,
        "genuineness": 4.319066047668457,
        "identity": 0.4580978751182556,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "465c7bbae2e7fe104d3fd0c1458c90d2cbcf29f0558c1be861bcc51152fbd1a1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "410fcee4d89e0ddf2724dafb39aabaa4f3885701cb88be42163b285cb880694c",
      "generation_seconds_batch": 25.310821790946648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0154500007629395,
        "target_z": 1.3437500945651428,
        "ce": 6.125868320465088,
        "genuineness": 4.306513786315918,
        "identity": 0.5835092663764954,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/465c7bbae2e7fe104d3fd0c1458c90d2cbcf29f0558c1be861bcc51152fbd1a1.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "465ddf902efd22eadac5995ec83aeca6815aab220d753d5ffae0efaae39a4c43",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "43fa4e9ce71ff56b84e366f643c566a04048eb5bf895ad8344da3f064934817a",
      "generation_seconds_batch": 16.402796934940852,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1166224479675293,
        "target_z": 0.6523436887475779,
        "ce": 6.427689552307129,
        "genuineness": 4.18099308013916,
        "identity": 0.3759012222290039,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/465ddf902efd22eadac5995ec83aeca6815aab220d753d5ffae0efaae39a4c43.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "468f8d3b181e2f062d1cc967f0f8c0f2c4f18f5413e021189e86455ac019eb20",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bf23aebf4221999e9ca8c95b790b51dbe0446340dfe04a2fdeef9c5629a36dcd",
      "generation_seconds_batch": 24.293049648054875,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.852950096130371,
        "target_z": 1.2187500601778183,
        "ce": 6.078212261199951,
        "genuineness": 4.287685871124268,
        "identity": 0.6405206918716431,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/468f8d3b181e2f062d1cc967f0f8c0f2c4f18f5413e021189e86455ac019eb20.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "473715ec281ce7e454c61e0bc5cbbffc3244c207e27cac0852e085577444aad9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6926e571c3d2c1cc8507ca7b119ead8f4047ceab210e7e3fd301bbbc3e422cc5",
      "generation_seconds_batch": 24.422291282913648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.467012882232666,
        "target_z": 0.9218750243576883,
        "ce": 6.252951145172119,
        "genuineness": 4.1998209953308105,
        "identity": 0.6563870906829834,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/473715ec281ce7e454c61e0bc5cbbffc3244c207e27cac0852e085577444aad9.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5cc53b3fb0201f5ef3d66309529b7256c0dee9794563fdb71852c08fd52b9f25",
      "generation_seconds_batch": 18.07494239101652,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8547096252441406,
        "target_z": -0.318359319299698,
        "ce": 6.157639026641846,
        "genuineness": 4.482243061065674,
        "identity": 0.7572577595710754,
        "hypothesis": "Quelqu'un a déplacé la petite chasse bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "47ecd49f89719943a7edfb445e1d1206725b16140ee12048b823222957e00643",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8cfbec6fde0d3314fa9340b104ed5cb4e3b4c104a166e076c52d0fe8b4c5c491",
      "generation_seconds_batch": 18.09012217808049,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6134988069534302,
        "target_z": -0.5039062625370455,
        "ce": 6.1020402908325195,
        "genuineness": 4.444586753845215,
        "identity": 0.8032065629959106,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/47ecd49f89719943a7edfb445e1d1206725b16140ee12048b823222957e00643.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "48550ded62499ca9c2cbc8808a5138b319e109e5d2029aee860e98a717766547",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b9602e123d80a8807fac60dcf0d0e3a1f3e5b0d20549909d9aa62c9dc1937b20",
      "generation_seconds_batch": 22.811471040011384,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.098459243774414,
        "target_z": -0.13085945111777603,
        "ce": 6.332377910614014,
        "genuineness": 4.444586753845215,
        "identity": 0.6297292113304138,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/48550ded62499ca9c2cbc8808a5138b319e109e5d2029aee860e98a717766547.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "48cc0d2f6275b1e93db487815fbbca71e99717878ad80fa7c11c2e0366ac7037",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5d763d0a07e68d3eb573392f0bdedfd90ec9821838c7b4c27e134239fa856a3a",
      "generation_seconds_batch": 23.246184922987595,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.221180438995361,
        "genuineness": 3.9048471450805664,
        "identity": 0.6166275143623352,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/48cc0d2f6275b1e93db487815fbbca71e99717878ad80fa7c11c2e0366ac7037.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "490e1afaeac45364082a2fc01711a1a7b8820310ed3b8625a1951e4fe456d0ba",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "d6427e18a88a4aa995d97eda902257cbe99cf33457249bae6b2fd6c223bd1513",
      "generation_seconds_batch": 24.669435556977987,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.421699523925781,
        "target_z": 1.6562499971343896,
        "ce": 6.308549880981445,
        "genuineness": 4.124508857727051,
        "identity": 0.5725626945495605,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/490e1afaeac45364082a2fc01711a1a7b8820310ed3b8625a1951e4fe456d0ba.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "49429295dcfb49ff58278973ec47d916852dab81c5142a120e3485b6414a7a37",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "812336d9b7a40c6c4ad537a947b4d1ad456258db32a1732b9d5d4bced3cda549",
      "generation_seconds_batch": 21.3543206009781,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7179901599884033,
        "target_z": 0.34570320290878254,
        "ce": 6.427689552307129,
        "genuineness": 4.168440818786621,
        "identity": 0.4309616684913635,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/49429295dcfb49ff58278973ec47d916852dab81c5142a120e3485b6414a7a37.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "13d65b21e62b4fffe8de175ff713d3edcea3d5bcf9163b42b9c19a15b13ed339",
      "generation_seconds_batch": 18.355023359996267,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4408427476882935,
        "target_z": -0.6367187302989286,
        "ce": 6.197352409362793,
        "genuineness": 4.243753433227539,
        "identity": 0.7421566843986511,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "49ec8701983022f994e401781648f7a233fa9ef61e431df659ebc55ce9f658f4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dca854d1ee6fe8b3035323e2789cd01a959e383204c3d02041277489d4073b10",
      "generation_seconds_batch": 23.150213941000402,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.056075096130371,
        "target_z": 1.3750001948615067,
        "ce": 5.959072113037109,
        "genuineness": 3.7667744159698486,
        "identity": 0.46672266721725464,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/49ec8701983022f994e401781648f7a233fa9ef61e431df659ebc55ce9f658f4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "4a585423231491580287a55a73816fff552a8bdbd29683fdb16986400e69ef5a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "215fca2a850b9a51abc8bbff0b57dfc3f2bd8a30b891a95c856e64f3a7ba4966",
      "generation_seconds_batch": 24.786747078993358,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8119354248046875,
        "target_z": 0.41796885352017543,
        "ce": 6.24500846862793,
        "genuineness": 4.344170093536377,
        "identity": 0.6578090786933899,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4a585423231491580287a55a73816fff552a8bdbd29683fdb16986400e69ef5a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "4bfc8219d0c77e48367a53cef235b032185af62586bdb7bca08de0eeffd7de26",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 132,
      "seconds_generated": 10.56,
      "mp3_sha256": "f24e65537dc3253615fd7939abf76b1ba6f1d4a253dc34458d9b4d0917285a30",
      "generation_seconds_batch": 24.803521528025158,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.2998247146606445,
        "target_z": 1.5625000630434287,
        "ce": 5.677107334136963,
        "genuineness": 3.587907314300537,
        "identity": 0.34031760692596436,
        "hypothesis": "Encontra la cajita. Estaba junto a la ventana vieja. Podemos mirar.",
        "wer": 0.4117647058823529,
        "duration_error_s": 0.3600000000000012,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4bfc8219d0c77e48367a53cef235b032185af62586bdb7bca08de0eeffd7de26.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "4c1ddb682c69ea796430c5ee616ecb8b188cb6ea0a449dd8a1c07f3fa700a5f3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "917df1cbc39e87e262f530dce0fac0df8d9896ce5f1c26b0d1d1a8959b460a50",
      "generation_seconds_batch": 23.735426774946973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2152562141418457,
        "target_z": -0.04101555031502916,
        "ce": 6.332377910614014,
        "genuineness": 4.293961524963379,
        "identity": 0.5913194417953491,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4c1ddb682c69ea796430c5ee616ecb8b188cb6ea0a449dd8a1c07f3fa700a5f3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "4c35f15495989db5e0ae1d06cac87934bc8ebb31b0098dc0fa24e09f90616267",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "3a8d9313c69361150431afca61397589ec0835a1fdd62868e9b8d3efa3ce3156",
      "generation_seconds_batch": 24.568017804063857,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.24500846862793,
        "genuineness": 4.080576419830322,
        "identity": 0.3371617794036865,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4c35f15495989db5e0ae1d06cac87934bc8ebb31b0098dc0fa24e09f90616267.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "4c44a54a3ff792fdd069574b146ceb315eb0566b70fb5f410f8c58fbc0d6effd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 134,
      "seconds_generated": 10.72,
      "mp3_sha256": "8c467fbc7460b97df36af913a137386332d35c57439176c8819ec91e8b59f290",
      "generation_seconds_batch": 21.34410384099465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.685761451721191,
        "target_z": 1.8593747320654284,
        "ce": 5.736677646636963,
        "genuineness": 4.149612903594971,
        "identity": 0.22186803817749023,
        "hypothesis": "It's a nice boy. It is pretty fenêtre. We've regarded enough.",
        "wer": 0.9473684210526315,
        "duration_error_s": 0.5200000000000014,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4c44a54a3ff792fdd069574b146ceb315eb0566b70fb5f410f8c58fbc0d6effd.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "4c4f678d75a33f21715a73b368d4127870287c236073afdf52ce1d60dd6b3f9c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "56b2d36a20bb1d10d8ae91906e28d76eac24462fbacb45d7aaf3576f151267d3",
      "generation_seconds_batch": 16.990720478002913,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4002177715301514,
        "target_z": -0.6679687388957597,
        "ce": 6.475345611572266,
        "genuineness": 4.017816066741943,
        "identity": 0.6010324358940125,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4c4f678d75a33f21715a73b368d4127870287c236073afdf52ce1d60dd6b3f9c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "4caae8ccbaeee85b8a590deaefafb99dccc7c00d2a3d27e24651d7426dc22167",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91db8f678aeeea3e8a15ccc6cfe2db346d887393d6728357ce54657af15d0894",
      "generation_seconds_batch": 24.721887089894153,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.009982109069824,
        "target_z": 0.5703125881175195,
        "ce": 6.300607204437256,
        "genuineness": 4.080576419830322,
        "identity": 0.4985029995441437,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4caae8ccbaeee85b8a590deaefafb99dccc7c00d2a3d27e24651d7426dc22167.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "4d1c49611e44c1496e001bf0bb29b985073ac5d98835c3b272692e72db9b8ba7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "71b196a21bf3257106954d95aa8c4d294d3f90b209f4d23cd8ba35733ed82450",
      "generation_seconds_batch": 24.397478452068754,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3130099773406982,
        "target_z": 0.03417971696205684,
        "ce": 5.879645347595215,
        "genuineness": 3.9676074981689453,
        "identity": 0.5555310249328613,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4d1c49611e44c1496e001bf0bb29b985073ac5d98835c3b272692e72db9b8ba7.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "4d1cd99f3b0bc14f2529ab9f9ee7394658f0fdc4b4a35d130073fb7b8bc9370e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "4b176a9566c619b0e6c9072f765de873cf13bc6f3611ee9e024b4d9d9593d13b",
      "generation_seconds_batch": 23.685987511998974,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.606271505355835,
        "target_z": 0.25976570219237993,
        "ce": 6.316492557525635,
        "genuineness": 4.394378662109375,
        "identity": 0.7620930671691895,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les, quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4d1cd99f3b0bc14f2529ab9f9ee7394658f0fdc4b4a35d130073fb7b8bc9370e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "4d7dd94530489400dd75f4126f69f0acd480e29fe7c0ecd77b762f6a73a8fd67",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4618ea16533f5625479d289cff0f19284947d90133a00c148261cd48f3a63cf2",
      "generation_seconds_batch": 23.732888206955977,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.5537309646606445,
        "target_z": 1.7578127313980392,
        "ce": 5.8875885009765625,
        "genuineness": 3.823258876800537,
        "identity": 0.5092999339103699,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4d7dd94530489400dd75f4126f69f0acd480e29fe7c0ecd77b762f6a73a8fd67.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "4dd09fe7017b1c21ad327e838c8156a0aaad88c9b9a135f117f1e1800c5a36a4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "535e5df08e30591c4cdf541eb48c0d9e2266547f786832b8b14197d59f478342",
      "generation_seconds_batch": 22.275149006047286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4767792224884033,
        "target_z": 0.16015616797190252,
        "ce": 6.435632705688477,
        "genuineness": 4.2751336097717285,
        "identity": 0.08133099973201752,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4dd09fe7017b1c21ad327e838c8156a0aaad88c9b9a135f117f1e1800c5a36a4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "4e0c245fc67394402c5bc2c5ea7e5b23c08f0ba0c0fbb881c6fadcc90b5a7fd3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "68ff6df5b316678149f0a9f9903141ad797a3d19162afb733237e0d12f4a7c9c",
      "generation_seconds_batch": 24.244613928021863,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.649825096130371,
        "target_z": 1.0624999254941299,
        "ce": 5.561938762664795,
        "genuineness": 3.785602569580078,
        "identity": 0.31303030252456665,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4e0c245fc67394402c5bc2c5ea7e5b23c08f0ba0c0fbb881c6fadcc90b5a7fd3.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "4e895c78987e28e826b8a60400db51c8334c2182670901e1ae19759ce027fffb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b425aa51c45ee783a4f1dd6f2e16a52436b658922da1bd7c14fcebd171a980db",
      "generation_seconds_batch": 22.474340933025815,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 6.268836498260498,
        "genuineness": 4.494794845581055,
        "identity": 0.6432632207870483,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4e895c78987e28e826b8a60400db51c8334c2182670901e1ae19759ce027fffb.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "4e8ff62bd8004c661dc0428e7a8e37129aec33decfac4e6ddd51fbcbf904c9bc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "22bc593869d020b17199e1ce0b8cdc9f534fbd23bfd73cc8aa99ead473dc5156",
      "generation_seconds_batch": 21.3543206009781,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6722869873046875,
        "target_z": 0.3105468859251396,
        "ce": 6.3641486167907715,
        "genuineness": 4.143336772918701,
        "identity": 0.6742256283760071,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4e8ff62bd8004c661dc0428e7a8e37129aec33decfac4e6ddd51fbcbf904c9bc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "4f1e79be067ebd89a5d83a15a5b3ab1782ee940123cea4942581eb386cd453e3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "3633375fa0544337e721f77a5f70eda2449542c64f9eae70cb6ab3a5f97dafe2",
      "generation_seconds_batch": 24.426237762905657,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.127168655395508,
        "target_z": 1.4296875952815455,
        "ce": 6.133810997009277,
        "genuineness": 4.055472373962402,
        "identity": 0.6119224429130554,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4f1e79be067ebd89a5d83a15a5b3ab1782ee940123cea4942581eb386cd453e3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "4fb54b807131d99d6e17d22d621603a84d5e7f280f4785ef92eccc76d632fcff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "683f3a636c2f4f4c30b3d8486bbede1322fd5a16f5a3c9cd99a691fedf57b4fe",
      "generation_seconds_batch": 24.070155836059712,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7310752868652344,
        "target_z": 1.1250001260868572,
        "ce": 6.062326908111572,
        "genuineness": 3.773050308227539,
        "identity": 0.39689651131629944,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/4fb54b807131d99d6e17d22d621603a84d5e7f280f4785ef92eccc76d632fcff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "50432c790affb3bd391233d2073efde93ac5c00191efa6277e8c57fcceb43d49",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3833281cc69b5817a787b72cb7e202ac58ed51f66e683ab5f5410bad0135f157",
      "generation_seconds_batch": 26.682299426058307,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.136545181274414,
        "target_z": -0.10156255086458446,
        "ce": 6.435632705688477,
        "genuineness": 4.21237325668335,
        "identity": 0.45228612422943115,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/50432c790affb3bd391233d2073efde93ac5c00191efa6277e8c57fcceb43d49.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "50598e99971e5a1d83201d6e462c37e215ce5bdd65d723a0bf9c5e105319dd5c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "1ac256ed4afea2a867a3b69ec9d478a0bb6719476e76b5171d004ad07ad9cbeb",
      "generation_seconds_batch": 24.56605463998858,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.984981060028076,
        "target_z": 1.3203124276433376,
        "ce": 6.1894097328186035,
        "genuineness": 4.15588903427124,
        "identity": 0.5216159820556641,
        "hypothesis": "I've trouved the petite boîte. Elle était près de la vieille fenêtre. We're going to be able to do it.",
        "wer": 0.5789473684210527,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/50598e99971e5a1d83201d6e462c37e215ce5bdd65d723a0bf9c5e105319dd5c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "5163a9eada92fd4fe0378d1e5a5e2b9dac8b6630a5e7c25f03baae746f6b7eba",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4c729e9a4f33cfb2fa11419710f13ee926112ea35c04691e24bcb08da8081568",
      "generation_seconds_batch": 24.255415681982413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 6.38797664642334,
        "genuineness": 3.961331605911255,
        "identity": 0.45866280794143677,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5163a9eada92fd4fe0378d1e5a5e2b9dac8b6630a5e7c25f03baae746f6b7eba.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "518124e95d565af0588359b807f47759f55ca2f206fdb7a3248d38ada7769418",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9b40ad5b33d63b2a8926c7e7c48ad7114236955764fa01c6f8e7ad2abb84fae4",
      "generation_seconds_batch": 15.910896452958696,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.056075096130371,
        "target_z": 1.3750001948615067,
        "ce": 6.221180438995361,
        "genuineness": 4.20609712600708,
        "identity": 0.5804981589317322,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/518124e95d565af0588359b807f47759f55ca2f206fdb7a3248d38ada7769418.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "5184bd335887045c3b5e527ff3209070ca7c8a3a27cf72fef3dae7d597a76f4d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9bc7d0c10473d0b8ba001554ac1d529908f3309d9901c1a9c8278db57e0a4b4d",
      "generation_seconds_batch": 24.561673025018536,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0455288887023926,
        "target_z": 0.597656288327539,
        "ce": 6.221180438995361,
        "genuineness": 4.243753433227539,
        "identity": 0.5370914936065674,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5184bd335887045c3b5e527ff3209070ca7c8a3a27cf72fef3dae7d597a76f4d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "5232116dbe937faeedaf6df19b50253b4d694944b50e510d832498dbebbe9075",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9d16dd409eca525a16db173376bab241ab58644cafd884518ee7b1846b084432",
      "generation_seconds_batch": 18.08075435901992,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 6.427689552307129,
        "genuineness": 4.545003414154053,
        "identity": 0.397128164768219,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5232116dbe937faeedaf6df19b50253b4d694944b50e510d832498dbebbe9075.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "524b31eb71408bf56809864aa0a80aeb3fb2f0e8800d45cb1f6c27fcad3948af",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d4fc24edf723d35df8c0cd7b35c7c33a8239f7c7d10acecdef68eaa462479885",
      "generation_seconds_batch": 20.737932084011845,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.182638168334961,
        "target_z": 0.7031250558794027,
        "ce": 6.221180438995361,
        "genuineness": 4.20609712600708,
        "identity": 0.6731656193733215,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/524b31eb71408bf56809864aa0a80aeb3fb2f0e8800d45cb1f6c27fcad3948af.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "525adcb156268d4771435b7cc51bd80e654221f1a84dcae91a1f8ff4a402132b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "d7cea6b53d4fcda9562bbb1359b987859cad1db1d20a146ce3f9c56c943bc92a",
      "generation_seconds_batch": 19.65025817102287,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.462324142456055,
        "target_z": 1.6874997306326232,
        "ce": 6.268836498260498,
        "genuineness": 4.444586753845215,
        "identity": 0.5085042119026184,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/525adcb156268d4771435b7cc51bd80e654221f1a84dcae91a1f8ff4a402132b.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "52610a1af39a90f02310d45f3b4fb8fb5fd768d6403b7e15f36bfad6b78891eb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4ac0cb2d4090cedef2c707b91aa57f296235dc3395702fa0bbfb27bdc5ea7eb8",
      "generation_seconds_batch": 17.743167817941867,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.743380546569824,
        "target_z": 0.3652342863451785,
        "ce": 6.221180438995361,
        "genuineness": 4.557555198669434,
        "identity": 0.6659924983978271,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/52610a1af39a90f02310d45f3b4fb8fb5fd768d6403b7e15f36bfad6b78891eb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "53371980fea71f11be82bc4e8715dcb08edd83cfde8b0cb099384b90a8bfd8e5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "58f3ab9defeab1c55733db1e84f10f9857fc0265e93738fecddc8987ca8b0a54",
      "generation_seconds_batch": 24.571042870054953,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.644357204437256,
        "target_z": 0.2890624190465064,
        "ce": 6.4912309646606445,
        "genuineness": 4.024092197418213,
        "identity": 0.38662728667259216,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/53371980fea71f11be82bc4e8715dcb08edd83cfde8b0cb099384b90a8bfd8e5.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "53689dc0a63a3cf5cf6b25ff22ed8f754b270658db1b3f110b03669032d31fa5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6307b384d7e443033b51e3a2ea1399e584369cb6891a772128863c0b47a7e62",
      "generation_seconds_batch": 16.548781483084895,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.54826283454895,
        "target_z": 0.9843750415513507,
        "ce": 6.23706579208374,
        "genuineness": 4.425758361816406,
        "identity": 0.669874906539917,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre, prends les quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/53689dc0a63a3cf5cf6b25ff22ed8f754b270658db1b3f110b03669032d31fa5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "53b7b6758a7f87ac9156f155f14669731bcc727d2b241ca269780e88d839dd16",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "33a6bc899814689e8d8bbdee10ae83079d3a0e76b247f57943796284cd5f0e2d",
      "generation_seconds_batch": 15.765736300963908,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.413937568664551,
        "target_z": 0.11181639259357548,
        "ce": 6.308549880981445,
        "genuineness": 4.319066047668457,
        "identity": 0.5694900751113892,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/53b7b6758a7f87ac9156f155f14669731bcc727d2b241ca269780e88d839dd16.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "53be9f817603b0b6a5391ed6b7587278b486feb546494907d4a05c33d98fb758",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a0432eb65f54050b52128e7e977b0649c7480ddb39479397b12086e1e8967631",
      "generation_seconds_batch": 23.685987511998974,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.238497495651245,
        "target_z": 0.7460938062376039,
        "ce": 6.23706579208374,
        "genuineness": 4.369274139404297,
        "identity": 0.787617564201355,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/53be9f817603b0b6a5391ed6b7587278b486feb546494907d4a05c33d98fb758.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "59d85a5653fc3157820093c7aa4f96744adbaabe3ec34c3bcf1d23ca8f9c6adb",
      "generation_seconds_batch": 17.954962073010392,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.7756088972091675,
        "target_z": -1.148437517910065,
        "ce": 6.141753673553467,
        "genuineness": 4.017816066741943,
        "identity": 0.5005091428756714,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "54b8c5f54d9cb8c70caefacedced040c260c040cb2e606a0612a7f4079f9c95f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fc8f80f65602eb36bf027d80d932386572be6d9e6d7e828252f7c5776f1af38b",
      "generation_seconds_batch": 31.469926080084406,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 6.38003396987915,
        "genuineness": 4.494794845581055,
        "identity": 0.34971335530281067,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/54b8c5f54d9cb8c70caefacedced040c260c040cb2e606a0612a7f4079f9c95f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "54bb97cbd4fe4273d0db414f626335799ccd5203723c980b4a379e609733bca4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "ba5937d07f3897e3ef03cf0ae95aaec405cadf6556e01a2bbdeb5a0b06348731",
      "generation_seconds_batch": 26.182251614052802,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.106856346130371,
        "target_z": 1.4140627285324288,
        "ce": 6.38797664642334,
        "genuineness": 4.457139015197754,
        "identity": 0.6655558347702026,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/54bb97cbd4fe4273d0db414f626335799ccd5203723c980b4a379e609733bca4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "54c300bae86e5be8537fe06461d182f0cd8586f8f0672e763e61770508492e62",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "6a7a8e40e920e04c7de811bf1f81a0759387ef06c37d53ce4ee8086f265be037",
      "generation_seconds_batch": 24.688469634973444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.492793083190918,
        "target_z": 1.7109373975544284,
        "ce": 5.871703147888184,
        "genuineness": 3.8797430992126465,
        "identity": 0.26814350485801697,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay detrás.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/54c300bae86e5be8537fe06461d182f0cd8586f8f0672e763e61770508492e62.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "55833995c2f4c5faa471275a669d937db7d28ca49369099c03cb8a778511de13",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2f68557204bb845cbc17e4d5dcd6ede7772807a3b4fc8c102bf749560d1476a9",
      "generation_seconds_batch": 23.87746356392745,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 5.911416053771973,
        "genuineness": 3.9927117824554443,
        "identity": 0.7490222454071045,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/55833995c2f4c5faa471275a669d937db7d28ca49369099c03cb8a778511de13.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "55f515535a9412f9c8cf717d57e3423d6c12ed68866111b3538eae800a7fc306",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "e3d18d2ae738fadf8aac4bfae5076301b265bfdc5b6fa0acbc1811d05302b80f",
      "generation_seconds_batch": 23.195553161902353,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.24500846862793,
        "genuineness": 4.469690799713135,
        "identity": 0.6221755743026733,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/55f515535a9412f9c8cf717d57e3423d6c12ed68866111b3538eae800a7fc306.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "567e3e82515f62f2f14970c9857e5888b136f677d8f99dca548588a2618660f8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c96be35c977c5a3aa9bcd89cbd44acfde19c9d5255cc960b13a828687901fa29",
      "generation_seconds_batch": 25.65415217494592,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6092002391815186,
        "target_z": 1.0312500085968312,
        "ce": 6.149696350097656,
        "genuineness": 3.5094566345214844,
        "identity": 0.5036886930465698,
        "hypothesis": "Ich habe die kleine Schacht gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.1875,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/567e3e82515f62f2f14970c9857e5888b136f677d8f99dca548588a2618660f8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "56b1df8205bf900e5a1c5825c2107f5dbf58c38a0b56644290b2e9832306400f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a3ea1df8125695fd79ddd13f6a6d2c45030db9c04c4f8f16bfe5afa70e451c43",
      "generation_seconds_batch": 16.74965383298695,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.568185567855835,
        "target_z": 0.23046880193918837,
        "ce": 6.229123115539551,
        "genuineness": 3.8169827461242676,
        "identity": 0.37284737825393677,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/56b1df8205bf900e5a1c5825c2107f5dbf58c38a0b56644290b2e9832306400f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "56cdd694dd80a5f658ea92d9d7168969e649738ebaf3e0f16550e4742d12874d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "7053bab91210c6b62a0bf772ba784d1268b1329d1636a2993ae92880bfd31065",
      "generation_seconds_batch": 21.48514655197505,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.055685043334961,
        "target_z": 0.6054687217020974,
        "ce": 5.283945083618164,
        "genuineness": 3.886019229888916,
        "identity": 0.17428188025951385,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/56cdd694dd80a5f658ea92d9d7168969e649738ebaf3e0f16550e4742d12874d.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "571caffce44e2dc4d73466477f84516ba3d60fc91b7a215504a2210cc0bed4e0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "65f0089442c4a71e3311da6fb9fbd913293c072feb75d834be8902d3a0477778",
      "generation_seconds_batch": 16.63328944996465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.872872829437256,
        "target_z": 0.46484382056565593,
        "ce": 6.340320587158203,
        "genuineness": 4.105680465698242,
        "identity": 0.6251718997955322,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/571caffce44e2dc4d73466477f84516ba3d60fc91b7a215504a2210cc0bed4e0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "5784e2b8bc7907df4d513f526bfeba30a55760bd5b0c52307dd4a59531f631af",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91c8b5968c34812c0706ffefeb8578bf084b6b20a5cc1ed8033cd1a6c07768f6",
      "generation_seconds_batch": 24.918187833041884,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3771212100982666,
        "target_z": 0.08349609236196996,
        "ce": 6.395919322967529,
        "genuineness": 4.519899368286133,
        "identity": 0.5189595222473145,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5784e2b8bc7907df4d513f526bfeba30a55760bd5b0c52307dd4a59531f631af.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "580d30a91b6e264e5a2919405c0cc9c03bd32bf16612e6fb9d2753ae030e948f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e87ff6cff37a02064b99a29defc35526dbb596d491a57848569aee7a67b2490e",
      "generation_seconds_batch": 24.880217383033596,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6295127868652344,
        "target_z": 1.046875058745013,
        "ce": 6.332377910614014,
        "genuineness": 3.798154592514038,
        "identity": 0.30639904737472534,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinaus.",
        "wer": 0.0625,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/580d30a91b6e264e5a2919405c0cc9c03bd32bf16612e6fb9d2753ae030e948f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "5834e25e01a0319e94e2c1e3666cd616aaca558fc17988be6088341348131abf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d45cbc816d042893fe2267c00aac52bdee94e1d0d2d8ab45b04d43a48529e8ff",
      "generation_seconds_batch": 23.195553161902353,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5199432373046875,
        "target_z": 0.1933592849123733,
        "ce": 6.070269584655762,
        "genuineness": 4.049196243286133,
        "identity": 0.7394423484802246,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5834e25e01a0319e94e2c1e3666cd616aaca558fc17988be6088341348131abf.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "58c732308ac86639026f577a6967e6f68a7f7ce34506ac6b7906672c14703ff4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "28ce4dab421d85fe33e1bb912c10116607eb6f51a4bb5eaff2f9bc5fd8546300",
      "generation_seconds_batch": 16.65904374793172,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.54826283454895,
        "target_z": 0.9843750415513507,
        "ce": 6.24500846862793,
        "genuineness": 4.494794845581055,
        "identity": 0.5699113011360168,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/58c732308ac86639026f577a6967e6f68a7f7ce34506ac6b7906672c14703ff4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "596ada69133b8d53282f900dba144efd7ace001d58883fd232c6b9253234681e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e77975b9ee498ebc636610b63ae4f2832ee3d816f41218791f244ec4309dfe79",
      "generation_seconds_batch": 22.46797705197241,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6722869873046875,
        "target_z": 0.3105468859251396,
        "ce": 6.435632705688477,
        "genuineness": 4.055472373962402,
        "identity": 0.5181562900543213,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/596ada69133b8d53282f900dba144efd7ace001d58883fd232c6b9253234681e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "59869a498586dfad0be8aeb334ff22db8ff42befbd6368f2ee26bb78c2deba70",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9527c55867efde86168eaca72d33d96acc167c9726a5a5f07547950507e620df",
      "generation_seconds_batch": 16.68076461099554,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.974824905395508,
        "target_z": 1.3124999942687792,
        "ce": 6.117925643920898,
        "genuineness": 4.162164688110352,
        "identity": 0.35481688380241394,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/59869a498586dfad0be8aeb334ff22db8ff42befbd6368f2ee26bb78c2deba70.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "598f99afd66c5be5901e4335286bf2d07bce5deb5cea342f034d1f6c4d61949d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "5355dc4abe7361ec5d7da510c8065f614fb4d1ec034089ec45e12431307eb3fc",
      "generation_seconds_batch": 21.48514655197505,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2943568229675293,
        "target_z": 0.7890625565958053,
        "ce": 5.02183723449707,
        "genuineness": 3.9299514293670654,
        "identity": 0.32877838611602783,
        "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je klaart.",
        "wer": 0.15789473684210525,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/598f99afd66c5be5901e4335286bf2d07bce5deb5cea342f034d1f6c4d61949d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "5a08b6964920131c52bc03cdfff7da26d0dbc8a5f688c0a1eea29e756c1d2980",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "08572b3b317bf9355ff14ff26b286f9a442b300b373f02c8cdd7942949244b68",
      "generation_seconds_batch": 24.597534175030887,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5279502868652344,
        "target_z": 0.9687499914031689,
        "ce": 6.1020402908325195,
        "genuineness": 4.243753433227539,
        "identity": 0.661386251449585,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5a08b6964920131c52bc03cdfff7da26d0dbc8a5f688c0a1eea29e756c1d2980.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "5a152a259a1d2b5f503f1388f2a8f23bc508e851a9cac94d4bec4da892d2ee9a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "abd1878cc20ad3a9e3deeabb7b040532552594b8fee9db5978e39e10e4356bb6",
      "generation_seconds_batch": 24.251674312050454,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 5.7406487464904785,
        "genuineness": 3.5722172260284424,
        "identity": 0.3391297459602356,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5a152a259a1d2b5f503f1388f2a8f23bc508e851a9cac94d4bec4da892d2ee9a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "5ad3c56c2d543eed7b05e70d4cbdab48ce0b2961435be3e064b6afd8cab9ed53",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "3cc27ba4eeba1de851627e767d8b0fbadbf5ef0642307c311888d27e17d2fa34",
      "generation_seconds_batch": 24.128403423936106,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3705286979675293,
        "target_z": 0.8476563571021885,
        "ce": 6.308549880981445,
        "genuineness": 4.193545341491699,
        "identity": 0.4889000654220581,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5ad3c56c2d543eed7b05e70d4cbdab48ce0b2961435be3e064b6afd8cab9ed53.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "5b2e747512d9c873b5a06a99c503fbc679507a4720cdae0c41b12738ea9d0f16",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "08a9433cea898d2c62fc12180c0482491475728a36db2508b2ab2e41b4904f83",
      "generation_seconds_batch": 15.910896452958696,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1924045085906982,
        "target_z": -0.05859380050638316,
        "ce": 6.173524379730225,
        "genuineness": 4.507347106933594,
        "identity": 0.6680805087089539,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5b2e747512d9c873b5a06a99c503fbc679507a4720cdae0c41b12738ea9d0f16.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "5b6381203537e11bc1d97635828c348bd802241fa13a7f8a5fb558f5d218eaa9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ee16708cbb4c682dd4d9168df7dfb6c97c57530a48906adf53bf74041ade82e6",
      "generation_seconds_batch": 24.594467393006198,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 5.974957466125488,
        "genuineness": 4.400654315948486,
        "identity": 0.12788325548171997,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5b6381203537e11bc1d97635828c348bd802241fa13a7f8a5fb558f5d218eaa9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "5beb6b31386b8340f68e26986f0a8a36c76620d0378c607fe544f85a2e64c1af",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "714f16548b7401e28fd89f1388a1b55957ac3ef335459a71f8f0c12fbadea5ec",
      "generation_seconds_batch": 18.153896252973936,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0506069660186768,
        "target_z": 0.6015625050148182,
        "ce": 6.149696350097656,
        "genuineness": 3.760498285293579,
        "identity": 0.5801291465759277,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5beb6b31386b8340f68e26986f0a8a36c76620d0378c607fe544f85a2e64c1af.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "5bff31d6482af17c044f597fb9a23d6a7c167a7bd58c1971b764f0f0630ecfad",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "abedbbd18d94d867e886913f7f75cab4f9ae6fb70e47725f3932e06de68031d7",
      "generation_seconds_batch": 17.561124850064516,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.27746319770813,
        "target_z": 0.006836016752037403,
        "ce": 6.324435234069824,
        "genuineness": 4.243753433227539,
        "identity": 0.7155251502990723,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5bff31d6482af17c044f597fb9a23d6a7c167a7bd58c1971b764f0f0630ecfad.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "5c16ab7e8d75abf4eda3f8d29addbe12fdddd2ac17e204b9b48ac19136d6c122",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "7ffef636894f2a6ff3bc29daf6ae93433b673d37634bff2c76b8865489287dc3",
      "generation_seconds_batch": 23.05518397805281,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.181467056274414,
        "genuineness": 3.9676074981689453,
        "identity": 0.6240097284317017,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5c16ab7e8d75abf4eda3f8d29addbe12fdddd2ac17e204b9b48ac19136d6c122.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "5cb01f7a284b75db41cfc399610b7e77f179565f9e81fd8b80e631ebd1122cdf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "3f3438a6fff8fa19767d8b47482194476c28d4c84a25cdadf07c18ddd8cf2e35",
      "generation_seconds_batch": 25.746281387051567,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.086154937744141,
        "genuineness": 4.337893962860107,
        "identity": 0.6527148485183716,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5cb01f7a284b75db41cfc399610b7e77f179565f9e81fd8b80e631ebd1122cdf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "5cb7ad05dd46370d54eede9d841ed7789d6ffd7fdc7ed1f90a082bf684e9b8a8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "adae251feff4ac7c687431b13c164c6652bdd15b00994201b357acd09532b051",
      "generation_seconds_batch": 22.054422570974566,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5787315368652344,
        "target_z": 1.007812525074091,
        "ce": 5.990842819213867,
        "genuineness": 3.6789097785949707,
        "identity": 0.5103834271430969,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5cb7ad05dd46370d54eede9d841ed7789d6ffd7fdc7ed1f90a082bf684e9b8a8.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "5cc2151adb37537a3aca02b5a43894d02593897de4dd9b26749cb9624353e406",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "98f62a23aee2533150fb610100a4998d7394828a8deccc791f23e0e655769a9b",
      "generation_seconds_batch": 16.39180539501831,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.314669132232666,
        "target_z": 0.804687423344922,
        "ce": 6.435632705688477,
        "genuineness": 4.15588903427124,
        "identity": 0.40182429552078247,
        "hypothesis": "Someone moved the little blue chair. It used to stand here. Beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5cc2151adb37537a3aca02b5a43894d02593897de4dd9b26749cb9624353e406.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "5cd6e0f81e03f792b611dd8520a00d0ffe8dfd2a930c9d4c9391c26b21254458",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d7fcd040db0e10354571bb533c2430d4096a4d7e7c2f76ba6994c82982539935",
      "generation_seconds_batch": 16.61870622402057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7818562984466553,
        "target_z": 1.1640624763587142,
        "ce": 6.1894097328186035,
        "genuineness": 4.105680465698242,
        "identity": 0.8246896266937256,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5cd6e0f81e03f792b611dd8520a00d0ffe8dfd2a930c9d4c9391c26b21254458.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "5cfa8709fa0bd80bad888a6b47c2ddcd631f9bc15dfcc7dd04235c25fcb33a73",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "532731513f64811824a821d0d31e5946da2dea378a7df5ea3eb99d5b970b9893",
      "generation_seconds_batch": 14.978412685915828,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6545135974884033,
        "target_z": 0.2968750358201299,
        "ce": 6.507116317749023,
        "genuineness": 4.570107460021973,
        "identity": 0.5774668455123901,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5cfa8709fa0bd80bad888a6b47c2ddcd631f9bc15dfcc7dd04235c25fcb33a73.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "5d908119ffbdfc5551861ddfd289b804f88c8c827f44facd2da0698bcfeef696",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "71a6ab2a3d7f2ff11a101a5fe9306fa5c752db00f060d38fc8126dafcef84d6f",
      "generation_seconds_batch": 16.68076461099554,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.340449333190918,
        "target_z": 1.5937497965416623,
        "ce": 6.133810997009277,
        "genuineness": 4.174716949462891,
        "identity": 0.4925794005393982,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5d908119ffbdfc5551861ddfd289b804f88c8c827f44facd2da0698bcfeef696.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f36da5065d49a2dc2aa81092f8d7e91ef448c2dbd7bc090a81bd2c52467505f2",
      "generation_seconds_batch": 19.34534896200057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.247874140739441,
        "target_z": -0.7851562482089935,
        "ce": 6.24500846862793,
        "genuineness": 4.268857479095459,
        "identity": 0.7239035964012146,
        "hypothesis": "La route tourne à gauche après le pont. Continue, jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "5e84cc0bced69a81f1cf12746fec8062ae0372d203cfceda765c5c338ea8caff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "743bee46202e9bcf7afd1b0ffa9c1da54eed3663d00ac37a4e6b1ef1f63e804b",
      "generation_seconds_batch": 25.20912540704012,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.233419418334961,
        "target_z": 0.7421875895503247,
        "ce": 6.046441555023193,
        "genuineness": 3.835810661315918,
        "identity": 0.17357274889945984,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5e84cc0bced69a81f1cf12746fec8062ae0372d203cfceda765c5c338ea8caff.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "5eb238d973a462e3c0c645c33e191c2e303982a7bc28c4ddfd94a58c91dcc06d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3abe6faad8ae4868a135bf0e351c65334ca65aa279a3d16c7dbcb6bd939afe53",
      "generation_seconds_batch": 16.557607111055404,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0963101387023926,
        "target_z": 0.6367188219984611,
        "ce": 6.348263263702393,
        "genuineness": 4.168440818786621,
        "identity": 0.6914446353912354,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5eb238d973a462e3c0c645c33e191c2e303982a7bc28c4ddfd94a58c91dcc06d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "5ec9f996fd55c6ea1039d1b589cf2b99bae52ab30b0ac65fd1bcfd8175700649",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fc2eba97febf1325cebc51817b91cfffa50bd060254f13b2e5a7c6dd1df456b3",
      "generation_seconds_batch": 24.406232776935212,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.852950096130371,
        "target_z": 1.2187500601778183,
        "ce": 5.959072113037109,
        "genuineness": 3.402764081954956,
        "identity": 0.5029541850090027,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5ec9f996fd55c6ea1039d1b589cf2b99bae52ab30b0ac65fd1bcfd8175700649.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "5f4d7fb17e47733a71b062599b9da57ec1c2ed8785884c3cd5f7d0333e03a425",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "63a936a8fcd94faa6ce60903d0c2cc08d412766037fb02ac51af0ab5f85aedc7",
      "generation_seconds_batch": 23.45693346695043,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5707244873046875,
        "target_z": 0.23242181858329541,
        "ce": 6.213237762451172,
        "genuineness": 4.030367851257324,
        "identity": 0.586388349533081,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/5f4d7fb17e47733a71b062599b9da57ec1c2ed8785884c3cd5f7d0333e03a425.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "6032596e3b91d01a9e18e6b061c2042a7b571d4ef1bbcdb74767cefd36706f46",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c72639eeb91c3027fc24c3b73ba449e915de53aa303e874da0f06c070b42e716",
      "generation_seconds_batch": 22.72094012994785,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.218574523925781,
        "target_z": 1.4999998624507012,
        "ce": 6.260893821716309,
        "genuineness": 4.118232727050781,
        "identity": 0.6845868825912476,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6032596e3b91d01a9e18e6b061c2042a7b571d4ef1bbcdb74767cefd36706f46.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "615dcaa7654a2c6cd7b48508d548b7cf43319a0fe646d0c4da5868b8cea9c8da",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "42b284dafff33af994eec03b0664aba02edf6cb01e1ed684030ec8651ccae0d1",
      "generation_seconds_batch": 19.020171663956717,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7738494873046875,
        "target_z": 0.38867195326698384,
        "ce": 6.340320587158203,
        "genuineness": 3.653805732727051,
        "identity": 0.28597140312194824,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/615dcaa7654a2c6cd7b48508d548b7cf43319a0fe646d0c4da5868b8cea9c8da.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "616b6094855670d29a5ac9ce52e3badae6d05d08da8a08e7b6eb4519c180d7ce",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e7405644fc92a8f95056ad15bc8d8fb1ee460454d77608238d1335f4a57e7342",
      "generation_seconds_batch": 24.49260006507393,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.848261833190918,
        "target_z": 1.9843751332508832,
        "ce": 5.935244083404541,
        "genuineness": 4.1998209953308105,
        "identity": 0.5313748121261597,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/616b6094855670d29a5ac9ce52e3badae6d05d08da8a08e7b6eb4519c180d7ce.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "61810ccb26838876ee27d069319ea4b118e99626909252926ae2d7a32daec5ff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "deca682ce8618eda93eb9863f807ef753baac0b4384ab8d7d07a49b388355829",
      "generation_seconds_batch": 21.02395355689805,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7408416271209717,
        "target_z": 0.36328126970107144,
        "ce": 6.1894097328186035,
        "genuineness": 4.250029563903809,
        "identity": 0.6502112150192261,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/61810ccb26838876ee27d069319ea4b118e99626909252926ae2d7a32daec5ff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "61ba02ac956f672b836ae66406262d64c9d774f24d9dabf50db1e556699d4271",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "840b383407bc81321233c1ebc9a1d3bcaf9e07352fa36a6a071fccda828e9745",
      "generation_seconds_batch": 24.54743218398653,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6904501914978027,
        "target_z": 1.0937500257904935,
        "ce": 6.284721851348877,
        "genuineness": 4.2751336097717285,
        "identity": 0.488972544670105,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/61ba02ac956f672b836ae66406262d64c9d774f24d9dabf50db1e556699d4271.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "61eb28f3b91f4ccfe8ca57177849f2a05ae2eaa598fa94016d6b0659dbd2bedb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "530d9ff37146128c3563a755073e250078a0b10fce44dac9c758900507787959",
      "generation_seconds_batch": 23.820414545945823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7107625007629395,
        "target_z": 1.1093748925396103,
        "ce": 5.9431867599487305,
        "genuineness": 3.860914945602417,
        "identity": 0.36135053634643555,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/61eb28f3b91f4ccfe8ca57177849f2a05ae2eaa598fa94016d6b0659dbd2bedb.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "61fa665466d9fefc0b19cf8af2d86abe2c8537c5c0eb161a94e5150aa338bf4a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "059ede7b2c72662a4c1ca1aa099f6c088fa70ac5aff5f0e03aa007aa669bbe32",
      "generation_seconds_batch": 16.61870622402057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3637912273406982,
        "target_z": 0.07324225063297894,
        "ce": 6.308549880981445,
        "genuineness": 4.281409740447998,
        "identity": 0.6574913859367371,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/61fa665466d9fefc0b19cf8af2d86abe2c8537c5c0eb161a94e5150aa338bf4a.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "623c8d91e82ca5add3ea887b8a027e65a3224da36f26071d403e197a97c292a4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "31de65693ebc8686dc4f8b7e70b49223e9ee3603f2aa2aae9f4349eb4d0ab8ba",
      "generation_seconds_batch": 23.863298756070435,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2431857585906982,
        "target_z": -0.019531266835461053,
        "ce": 6.356205940246582,
        "genuineness": 4.20609712600708,
        "identity": 0.501961350440979,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zum kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.09523809523809523,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/623c8d91e82ca5add3ea887b8a027e65a3224da36f26071d403e197a97c292a4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "62d5dc08037e0d3804fec6ab17022d0b6859854bf786e4f0717e27c473c24062",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "291c18584090b7785fe68b59e35c31b963f080de1587a074392d3d4a39b3013c",
      "generation_seconds_batch": 24.019897302030586,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.42130970954895,
        "target_z": 0.8867187073740455,
        "ce": 6.252951145172119,
        "genuineness": 3.5690791606903076,
        "identity": 0.4741148352622986,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/62d5dc08037e0d3804fec6ab17022d0b6859854bf786e4f0717e27c473c24062.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "62ee84fad363027c44fdbb4744c399abee64f50b6e70dd6176689e65b6ff60e0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ba32a9de9e333b2d6f234294df20520e6359a017d3cdccfc3521e9421672ce46",
      "generation_seconds_batch": 22.038111016037874,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.687521457672119,
        "target_z": 0.32226571938604226,
        "ce": 5.871703147888184,
        "genuineness": 4.017816066741943,
        "identity": 0.30610302090644836,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/62ee84fad363027c44fdbb4744c399abee64f50b6e70dd6176689e65b6ff60e0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "631a85d120180192a423f60e41d8982861f0cb368ccb4b194c829463434c6694",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0461933ac485dbe86359cfa2229539840a34f349e4d761dfd44fcf3f5fa92fa8",
      "generation_seconds_batch": 24.618533052969724,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9951374530792236,
        "target_z": 1.328125044416961,
        "ce": 5.728734970092773,
        "genuineness": 3.660081624984741,
        "identity": 0.49178528785705566,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/631a85d120180192a423f60e41d8982861f0cb368ccb4b194c829463434c6694.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "631aa97326b2e60cd7396365d5cb39767840aacb5e3f8bae07b17223ad0bae59",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "514b02fe048b7ae87970155bc5bc2f6825f59ee7aaba5119fe9ed7a877b44d37",
      "generation_seconds_batch": 31.567206152016297,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9138875007629395,
        "target_z": 1.2656250272232987,
        "ce": 6.308549880981445,
        "genuineness": 4.337893962860107,
        "identity": 0.5108263492584229,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/631aa97326b2e60cd7396365d5cb39767840aacb5e3f8bae07b17223ad0bae59.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "631e1bb9cbd60f2bb160ab0e1a1375e180e98a04214d4ac2727f4c648eee4e84",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ee0e8539f4446d84e056ab660589a2dde06d3e423b7a0d903bed060248139c44",
      "generation_seconds_batch": 23.528223672998138,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.543184757232666,
        "target_z": 0.9804688248640715,
        "ce": 6.229123115539551,
        "genuineness": 4.482243061065674,
        "identity": 0.6317703723907471,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/631e1bb9cbd60f2bb160ab0e1a1375e180e98a04214d4ac2727f4c648eee4e84.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "633008ea8f7317796c5f9623b625c2fdc6074a579886129f18a7974e65e2436c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "adb4d993341d629854449997edba8d1641e7626b7c524615560373eea3c612e0",
      "generation_seconds_batch": 24.424419428920373,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.1474809646606445,
        "target_z": 1.4453124620306623,
        "ce": 6.284721851348877,
        "genuineness": 4.074300289154053,
        "identity": 0.5932344198226929,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/633008ea8f7317796c5f9623b625c2fdc6074a579886129f18a7974e65e2436c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "637a98b00369b99a4b8d430ec38f9f679befaa8c63bad4949b9141cf7e496eec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5885d08802d9067514bd04a6b175c767e1b58266884c52fb56d22a23775dd200",
      "generation_seconds_batch": 18.432599129038863,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4314661026000977,
        "target_z": 0.8945313241476689,
        "ce": 5.998785495758057,
        "genuineness": 3.5220088958740234,
        "identity": 0.17755842208862305,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/637a98b00369b99a4b8d430ec38f9f679befaa8c63bad4949b9141cf7e496eec.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "6398c6f928a1f4e324f598086f38d8d282bd9758593fd4b213692dd78c27417c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cef77d5e2d4d4f31fe063986e984d919514a246e941fe30d63a288a942f57624",
      "generation_seconds_batch": 16.507789566065185,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.009982109069824,
        "target_z": 0.5703125881175195,
        "ce": 6.260893821716309,
        "genuineness": 4.218649387359619,
        "identity": 0.5263019800186157,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6398c6f928a1f4e324f598086f38d8d282bd9758593fd4b213692dd78c27417c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "63cfbca2c450d9245062470a9e2561b57e0e8ed657b7714e32b047457f5ce249",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "49b56e0bdf1210e8d6161520217281e2e6295d481aeb62069255c11947862632",
      "generation_seconds_batch": 20.829184788977727,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6396689414978027,
        "target_z": 1.0546874921195715,
        "ce": 6.221180438995361,
        "genuineness": 4.218649387359619,
        "identity": 0.5333948731422424,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/63cfbca2c450d9245062470a9e2561b57e0e8ed657b7714e32b047457f5ce249.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "6461d2834daf40ce0b1fe8c220edfcadb68fba8ea107e15b541ad0e0bf23692c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c18ec3fa7a8adc439fca01215a6827a5f1697291e78c618589df074dc908871c",
      "generation_seconds_batch": 18.35334483999759,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.041330575942993,
        "target_z": -0.17480461809849832,
        "ce": 6.467403411865234,
        "genuineness": 4.093128204345703,
        "identity": 0.4241642951965332,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6461d2834daf40ce0b1fe8c220edfcadb68fba8ea107e15b541ad0e0bf23692c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "646a0158e22266bc214a791230ffbeecb751f414c47c60916752b559d594ac49",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "181f5c81a54869d8f01b69b45b6d1b18fc9890357a104384c47159385dce0f66",
      "generation_seconds_batch": 25.15952368208673,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.78908371925354,
        "target_z": 0.4003906033288214,
        "ce": 6.268836498260498,
        "genuineness": 4.143336772918701,
        "identity": 0.5994213819503784,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/646a0158e22266bc214a791230ffbeecb751f414c47c60916752b559d594ac49.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "655cd213e2e74e5c7d2d222aeea80ce37ef62e77611ec8b366ab235e03188f8a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6eb3b64b3e3c83ba5bd83a53a2e8dd288baa011582434f9cbf04324fc47437a7",
      "generation_seconds_batch": 24.523544859024696,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 5.998785495758057,
        "genuineness": 4.3127899169921875,
        "identity": 0.6865601539611816,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/655cd213e2e74e5c7d2d222aeea80ce37ef62e77611ec8b366ab235e03188f8a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "65c4cacd027a767c3bc1024df1c6b343ffbd7eac549553cd33c8848f6d891122",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "9ccb870f69cb3e77d983c38572786d66d5f4b169084d3fe433f6e877c2c36950",
      "generation_seconds_batch": 25.335343730053864,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.218574523925781,
        "target_z": 1.4999998624507012,
        "ce": 6.133810997009277,
        "genuineness": 3.798154592514038,
        "identity": 0.5400196313858032,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/65c4cacd027a767c3bc1024df1c6b343ffbd7eac549553cd33c8848f6d891122.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "65f5e21b1bdae632575e67636a8ca9db1f8abc04bf10db76c2d4ccbb083d4176",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ce412819149699e26fa4be6123bae5893cde4ef6648731099a77b48c3565563b",
      "generation_seconds_batch": 21.708112930995412,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.324435234069824,
        "genuineness": 4.042920112609863,
        "identity": 0.6204966902732849,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/65f5e21b1bdae632575e67636a8ca9db1f8abc04bf10db76c2d4ccbb083d4176.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "6601516c8d88468e1f63a61b4f688cc2c1de11086d8fc0403d6a35b3c14cc32a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6d01e1247a6340ddf26e46d67e4d631cfae602841cd51e50e0b43afbd2cb58c",
      "generation_seconds_batch": 16.35636682494078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.410763740539551,
        "target_z": 0.10937498423914284,
        "ce": 6.395919322967529,
        "genuineness": 4.432034492492676,
        "identity": 0.5132968425750732,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6601516c8d88468e1f63a61b4f688cc2c1de11086d8fc0403d6a35b3c14cc32a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "66829c4f57c5d5ac49fc7896d1bf5a067c4735826b897ba631f5dfcfa3e53b58",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "80b35b7e3b0a8a23b88af46a210f573256078e0fe6186e51e79253341ae32a5e",
      "generation_seconds_batch": 24.669435556977987,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.365450382232666,
        "target_z": 0.8437499570158441,
        "ce": 6.260893821716309,
        "genuineness": 4.21237325668335,
        "identity": 0.5476332306861877,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/66829c4f57c5d5ac49fc7896d1bf5a067c4735826b897ba631f5dfcfa3e53b58.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "6698866a0ab5a5f0056aeb6cf162827a38d991f4ec27456d54ff4488a02dd09f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e5501e2a88207d71c54a7bbdf6970d61afbb8c876e9873f331f79e1e08a94bb1",
      "generation_seconds_batch": 22.84294115693774,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.852950096130371,
        "target_z": 1.2187500601778183,
        "ce": 5.752562999725342,
        "genuineness": 4.243753433227539,
        "identity": -0.026301566511392593,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6698866a0ab5a5f0056aeb6cf162827a38d991f4ec27456d54ff4488a02dd09f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "67315d9ad639ceb756fb1af6998f003729e8bd6496657f31957e2c10ee403e12",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e39e110026a7385af7ebf6e81228c3b256c891648f54c22656f9a2f912c43c0f",
      "generation_seconds_batch": 25.158286132034846,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.517794132232666,
        "target_z": 0.9609375580286105,
        "ce": 5.974957466125488,
        "genuineness": 4.149612903594971,
        "identity": 0.4763604998588562,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/67315d9ad639ceb756fb1af6998f003729e8bd6496657f31957e2c10ee403e12.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "676ebdc2e4fa21b4368122321337d717a2b140d8dcdbac3e2558002792581f7a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ab4c84c78d34305c356522073ca1b683c2939c07de1a6dc4a4fbd1200128f442",
      "generation_seconds_batch": 23.821577762020752,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.106466293334961,
        "target_z": 0.6445312553730195,
        "ce": 6.165581703186035,
        "genuineness": 4.494794845581055,
        "identity": 0.6757354736328125,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/676ebdc2e4fa21b4368122321337d717a2b140d8dcdbac3e2558002792581f7a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "678e9de799851d484a989708dcaa61b559b5de95dd32b4f55cecaa6c5cbcfa18",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "1b2415f0276c7a46b9a63836228b1df89814d924e798c4cd207724b8e2ee3d1f",
      "generation_seconds_batch": 17.219861789955758,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 5.051386833190918,
        "target_z": 2.140625267934572,
        "ce": 6.252951145172119,
        "genuineness": 4.331617832183838,
        "identity": 0.5113350749015808,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what she contient.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/678e9de799851d484a989708dcaa61b559b5de95dd32b4f55cecaa6c5cbcfa18.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "67c977645aa00d5a760c9e5431c888cae8487a2c0d96bedf95a12c1c2834ae19",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "26c4776050d872369a63c1da1e75e27c568f67e06eb5687f35c6f82acbbfa0cd",
      "generation_seconds_batch": 25.005971884937026,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8627164363861084,
        "target_z": 0.45703120379203244,
        "ce": 6.078212261199951,
        "genuineness": 4.093128204345703,
        "identity": 0.608507513999939,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/67c977645aa00d5a760c9e5431c888cae8487a2c0d96bedf95a12c1c2834ae19.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "6841d32e1f3b06d574a14d9d9599bde7820f7c1467c42950ef78119c4f929d0e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "d0b74967c599a3bb2dbcab2cab5a66b6fac78151c1b8fa3a632e936d47ece152",
      "generation_seconds_batch": 24.76331339799799,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.618966579437256,
        "target_z": 0.2695311522110454,
        "ce": 6.403861999511719,
        "genuineness": 4.068024158477783,
        "identity": 0.5398440361022949,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6841d32e1f3b06d574a14d9d9599bde7820f7c1467c42950ef78119c4f929d0e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "6858ef58baca097a59ad21a380ad894a775bf0146cc2a00e95426af20df19052",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5a5b06936857fddf5c833e9a4aa934c741792d157ad617c2b708d3ccf97c6ff0",
      "generation_seconds_batch": 23.45672419492621,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.758615016937256,
        "target_z": 0.37695311980608115,
        "ce": 6.252951145172119,
        "genuineness": 3.9927117824554443,
        "identity": 0.29996004700660706,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6858ef58baca097a59ad21a380ad894a775bf0146cc2a00e95426af20df19052.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "68ec9202a35b398bbe72672d1b91a80dbdc0840aed0ae08ea38dbd4125b85b7f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9b3b84f3936bc89ee98b8f936e6ab1bcc3459ddc1d70e3f45d59cc9b12d7a9c1",
      "generation_seconds_batch": 23.37026508897543,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 6.1894097328186035,
        "genuineness": 4.049196243286133,
        "identity": 0.6932439208030701,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/68ec9202a35b398bbe72672d1b91a80dbdc0840aed0ae08ea38dbd4125b85b7f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "68f5c229975f0bfbc50128a97e5c7d12832e0cb52dc0e47e05351cb48b8cee9e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "79d671eef99332bc92c3d36aa855e68ebd1d54fb0c281f37990e9529e6e0ba04",
      "generation_seconds_batch": 18.423131512012333,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1420130729675293,
        "target_z": 0.6718749555830389,
        "ce": 6.157639026641846,
        "genuineness": 4.319066047668457,
        "identity": 0.7124993801116943,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/68f5c229975f0bfbc50128a97e5c7d12832e0cb52dc0e47e05351cb48b8cee9e.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "690d42b0f99ee419e43ec63dda3ab06d6c5e27e11e24d8e04df08d11cd350cea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fb59fe49bb5b665a591588d9337870ea59f84e7ebc7094b13485a1f093101afe",
      "generation_seconds_batch": 16.330921988002956,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8881070613861084,
        "target_z": 0.47656247062749346,
        "ce": 6.41180419921875,
        "genuineness": 4.293961524963379,
        "identity": 0.33577391505241394,
        "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/690d42b0f99ee419e43ec63dda3ab06d6c5e27e11e24d8e04df08d11cd350cea.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "693b197d0d49474298a525eb90ab61b562532ebb29f1261d64fc3158bb1f5989",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3ad2fc8deb7fae3dec8aa335f7e829fd5c51f9a447b57efd75555b01c6d8073b",
      "generation_seconds_batch": 23.608127934043296,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.928731918334961,
        "target_z": 0.5078123875247921,
        "ce": 6.23706579208374,
        "genuineness": 4.118232727050781,
        "identity": 0.2881813645362854,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/693b197d0d49474298a525eb90ab61b562532ebb29f1261d64fc3158bb1f5989.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "6964806283c473f8621b57d1a55610112f77803cb43d63bf9e5159412aafd41e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "91279b008be2b7e27ac2ee971756aff438cbe55c26c87eb3a9c500fccd1182ef",
      "generation_seconds_batch": 20.829184788977727,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2435755729675293,
        "target_z": 0.7500000229248831,
        "ce": 6.205295085906982,
        "genuineness": 4.143336772918701,
        "identity": 0.46025002002716064,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6964806283c473f8621b57d1a55610112f77803cb43d63bf9e5159412aafd41e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "69908de6086f29773cd4f5dbcd2d75bc1936b79fe71fca82fbb32bab91440d3e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8d762af4a05a2de57d76099b4ec9be16279415374f7d5e654492518f1e88c65e",
      "generation_seconds_batch": 17.88839563005604,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6845924854278564,
        "target_z": -0.44921877041747404,
        "ce": 6.229123115539551,
        "genuineness": 4.193545341491699,
        "identity": 0.32574141025543213,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/69908de6086f29773cd4f5dbcd2d75bc1936b79fe71fca82fbb32bab91440d3e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "699e660b67f8a75746be45476f9b706880014dd54a0d35e63c321c03519475c4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "926a9eee2835c1561b10885760113b36a1652125a9da506f95f9fc05c17c4d12",
      "generation_seconds_batch": 24.53825893404428,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.44670033454895,
        "target_z": 0.9062499742095065,
        "ce": 5.661221981048584,
        "genuineness": 3.7165660858154297,
        "identity": 0.25939780473709106,
        "hypothesis": "Hiep het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen.",
        "wer": 0.2222222222222222,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/699e660b67f8a75746be45476f9b706880014dd54a0d35e63c321c03519475c4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "69b6b3a23539a466ea1455119218f6aefeb7a97f2f57caea9f9fb1a2de4fcba6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "93db08a8c14f25a11929046db00f30e133d2d38eb8a9d75f10ddb572ce17d6c6",
      "generation_seconds_batch": 23.953770341002382,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7818562984466553,
        "target_z": 1.1640624763587142,
        "ce": 6.284721851348877,
        "genuineness": 4.168440818786621,
        "identity": 0.33091044425964355,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/69b6b3a23539a466ea1455119218f6aefeb7a97f2f57caea9f9fb1a2de4fcba6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "6a3bbaed0e079111a670779226e4c740faf8d528366cc635ce1edf22613d8365",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bc144a97d795db9af4b9ffcc386f1919fc7cbd4e04cfa56212fded1825c5c54b",
      "generation_seconds_batch": 31.838294808985665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.512326240539551,
        "target_z": 0.18750005158098706,
        "ce": 6.268836498260498,
        "genuineness": 3.9299514293670654,
        "identity": 0.2097187042236328,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6a3bbaed0e079111a670779226e4c740faf8d528366cc635ce1edf22613d8365.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5ed5cd0e5b99c4c1b63f61b9f950df39a55425cf25072f73c85f2cf9eff58dac",
      "generation_seconds_batch": 18.27715502900537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6033425331115723,
        "target_z": -0.5117187876111364,
        "ce": 6.300607204437256,
        "genuineness": 4.193545341491699,
        "identity": 0.4360619783401489,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "6a80a4273b059d2bac2be344c9529156df7a30f5db1ef5ee99decf87499ac405",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "847b06ee990a9ef9db9dc29ba503a59288b74afd2e71b9494c62e403c97d56d8",
      "generation_seconds_batch": 17.64175843098201,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0455288887023926,
        "target_z": 0.597656288327539,
        "ce": 6.1894097328186035,
        "genuineness": 3.7416701316833496,
        "identity": 0.35058051347732544,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6a80a4273b059d2bac2be344c9529156df7a30f5db1ef5ee99decf87499ac405.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "6adab0d7b83550af6a0076db689d0c7f3e8b688b98d27fb9de909a0517da7ef1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1fcc9676f315205ef0324b2792d77c2e22393661f8ddfb0b2a41827c8603ea11",
      "generation_seconds_batch": 22.153304339037277,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.29015851020813,
        "target_z": 0.016601650169767928,
        "ce": 6.109982967376709,
        "genuineness": 4.093128204345703,
        "identity": 0.5412766933441162,
        "hypothesis": "Escribí el número en el sobre, léelo viene y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.05263157894736842,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6adab0d7b83550af6a0076db689d0c7f3e8b688b98d27fb9de909a0517da7ef1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "6b2346b39b1bb74535c0e523c612c20a678fb9e33bec4c90c5fbb4955d76929d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "71c16ddd10e164d892c95af523e40d260e3998c7fab4c86377387503517c20a6",
      "generation_seconds_batch": 23.170147718978114,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9951374530792236,
        "target_z": 1.328125044416961,
        "ce": 6.292664527893066,
        "genuineness": 3.8671910762786865,
        "identity": 0.4047338664531708,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside.",
        "wer": 0.0625,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6b2346b39b1bb74535c0e523c612c20a678fb9e33bec4c90c5fbb4955d76929d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "6b3492fb50fb9f7c093e004325720b71d2576f3ac4765c1ae24df84b2193a1a4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6dbbfcde38c48c047c3a1e1e3206648a7ed1cb1538271da9c60ac04bed3b2429",
      "generation_seconds_batch": 18.344505004002713,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.720918893814087,
        "target_z": 1.1171875093132337,
        "ce": 6.109982967376709,
        "genuineness": 4.042920112609863,
        "identity": 0.3494833707809448,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6b3492fb50fb9f7c093e004325720b71d2576f3ac4765c1ae24df84b2193a1a4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "6b3f78dec38fffaffefcd68faf90a3932323e214db26fbfbeff732177df259ac",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e76243d23b5db804f093f2b1fdf04763622c30e3da84aff0c4f44e7b5adf9127",
      "generation_seconds_batch": 23.09460685995873,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.131856918334961,
        "target_z": 0.6640625222084805,
        "ce": 6.372091293334961,
        "genuineness": 4.306513786315918,
        "identity": 0.6621859073638916,
        "hypothesis": "",
        "wer": 1.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6b3f78dec38fffaffefcd68faf90a3932323e214db26fbfbeff732177df259ac.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "6b7b52d948d627f552365fd9696f212f0d0b89b1feb3e0151f4a16eb4e1237aa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0f9830a6e10aff90dfa0a41cacf49d96990f80c5602674cb0564f22ad504e774",
      "generation_seconds_batch": 16.727655808092095,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.162325620651245,
        "target_z": 0.6875000057312208,
        "ce": 6.221180438995361,
        "genuineness": 4.369274139404297,
        "identity": 0.44140058755874634,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6b7b52d948d627f552365fd9696f212f0d0b89b1feb3e0151f4a16eb4e1237aa.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c8ffe644829912c616d90cfaa3d541d1a4e20b8f9d25eff3d83a550ec1e2a45f",
      "generation_seconds_batch": 19.093078062986024,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.902951717376709,
        "target_z": -0.28124998567194803,
        "ce": 6.117925643920898,
        "genuineness": 4.6203155517578125,
        "identity": 0.6083920001983643,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "6c38651ef08b52e25c0fb90cd0656fb389703afcc10bcf35d302255b5990f42f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "150c0f546ac6101456ded75e4b6d8dc880d202c05d968b2390127dd3971e0e42",
      "generation_seconds_batch": 23.222925978014246,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 6.205295085906982,
        "genuineness": 4.268857479095459,
        "identity": 0.47425198554992676,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6c38651ef08b52e25c0fb90cd0656fb389703afcc10bcf35d302255b5990f42f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "6c3b951aa2b595b7145a46e05b4cf5bb5d77da391223252493600f5397ccea9c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4c6a31314768f01222e7890a518d88388c1385c899c18f1f9ddda6a7815d3949",
      "generation_seconds_batch": 29.48329180595465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.213106870651245,
        "target_z": 0.7265625394021429,
        "ce": 6.070269584655762,
        "genuineness": 3.7667744159698486,
        "identity": 0.5654221177101135,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6c3b951aa2b595b7145a46e05b4cf5bb5d77da391223252493600f5397ccea9c.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "6c603a04d1eeafa0b023ce913658ed5c60577fd956eed5130dcba0c0e8528a31",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "f2d73bd0ec96dbc96d7f3cee09e4b8072a6d93bd8363f0777d0cc21628459a3b",
      "generation_seconds_batch": 16.519894335069694,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.78908371925354,
        "target_z": 0.4003906033288214,
        "ce": 6.340320587158203,
        "genuineness": 4.20609712600708,
        "identity": 0.6504601240158081,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6c603a04d1eeafa0b023ce913658ed5c60577fd956eed5130dcba0c0e8528a31.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "6da43d937bd5e9c8c9e3a345f31dd493b4311351a47262466e654d2564847c74",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "439f16058de0ceef00f4e4e981de78d132864d23ce733fe99e375f270711cd9e",
      "generation_seconds_batch": 25.00551747600548,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7310752868652344,
        "target_z": 1.1250001260868572,
        "ce": 6.181467056274414,
        "genuineness": 4.21237325668335,
        "identity": 0.6334413290023804,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6da43d937bd5e9c8c9e3a345f31dd493b4311351a47262466e654d2564847c74.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "6ddc8a1acaf148ea8ccc2635db665a521fdc4604dd6d6056538aa0ac3173312d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "57abb16d149b33bb04b654079f60004193b4fbdc86b66996ae27163622baf283",
      "generation_seconds_batch": 24.54388007707894,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.258810043334961,
        "target_z": 0.7617188563857858,
        "ce": 6.213237762451172,
        "genuineness": 4.18099308013916,
        "identity": 0.4494391679763794,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6ddc8a1acaf148ea8ccc2635db665a521fdc4604dd6d6056538aa0ac3173312d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "6e09a3efc6e7f284ba79cff9ed2df517864b375c22990041cc87e1027dcb2026",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "76a0129d7cb418e2958baf91f81aaaf9d9654a5c9860aa3668c5a8068345ff17",
      "generation_seconds_batch": 23.109849028056487,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0210180282592773,
        "target_z": -0.19042966824668017,
        "ce": 6.1020402908325195,
        "genuineness": 3.9676074981689453,
        "identity": 0.7258801460266113,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6e09a3efc6e7f284ba79cff9ed2df517864b375c22990041cc87e1027dcb2026.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "6e8e46d59d9fb6f19b293c8ea3f7e4a84c581255a423625afb559fadbda0169e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "da6b9053977a1fd466869566a5757371ca098845c60484656b1528516ae7b3df",
      "generation_seconds_batch": 17.804942399961874,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.467012882232666,
        "target_z": 0.9218750243576883,
        "ce": 6.427689552307129,
        "genuineness": 4.3881025314331055,
        "identity": 0.4162420630455017,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together,",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6e8e46d59d9fb6f19b293c8ea3f7e4a84c581255a423625afb559fadbda0169e.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "6eb63dfa721c1da2b7d33f3938df097dea2e59aa04c945d517c662090df83366",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5360c31377ef624b5ec42b1207fe03f224482ced46decae96cf3cad3b7a14eac",
      "generation_seconds_batch": 16.604130673920736,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.599043846130371,
        "target_z": 1.0234373918232078,
        "ce": 6.157639026641846,
        "genuineness": 4.111956596374512,
        "identity": 0.7818405628204346,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6eb63dfa721c1da2b7d33f3938df097dea2e59aa04c945d517c662090df83366.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "6f1fda83d40b3b5ae8f6fca00f2a2d7aa3a371cf3ba0618ee61dd00d69236c0e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "899a12f2cd6d5383eb7b0b724946a3f698d698d4bfa48482d0e96a5df533b41f",
      "generation_seconds_batch": 24.00645129790064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.360762119293213,
        "target_z": 1.6093750300889091,
        "ce": 6.109982967376709,
        "genuineness": 4.011539936065674,
        "identity": 0.34529441595077515,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6f1fda83d40b3b5ae8f6fca00f2a2d7aa3a371cf3ba0618ee61dd00d69236c0e.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "6f729dbfd375b4e94b788162e29d8e36b5b8ef31035d1e3f95ef5a579018f8ea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eb8c2da7d06cc9cfc1bee990bfb562fdde533588a4d890a43ad708fb59fb367c",
      "generation_seconds_batch": 16.330921988002956,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.471701145172119,
        "target_z": 0.15624995128462332,
        "ce": 6.459460258483887,
        "genuineness": 4.18099308013916,
        "identity": 0.5242512226104736,
        "hypothesis": "Die Schlüss liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.14285714285714285,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6f729dbfd375b4e94b788162e29d8e36b5b8ef31035d1e3f95ef5a579018f8ea.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "6fa591c98c9e1850068a639cbed4ad9f411b24de9d4a249008350850cec7a074",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "977107d75d31714496f6bd91b5e9606d58fec511cd88ff1d57b76afd88e1f0b1",
      "generation_seconds_batch": 17.559631027979776,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6388894319534302,
        "target_z": -0.48437499570158443,
        "ce": 6.332377910614014,
        "genuineness": 3.6789097785949707,
        "identity": 0.45013362169265747,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag, lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6fa591c98c9e1850068a639cbed4ad9f411b24de9d4a249008350850cec7a074.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "6ff2ffc745db1b0681db6a125813b916d323025c875d1616698f630ca0a430a5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8156cbd1c30a3f094b2b39c0f7917697a63551d57063f9ed03349f78911a47d7",
      "generation_seconds_batch": 24.69119016698096,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4060754776000977,
        "target_z": 0.8750000573122079,
        "ce": 6.078212261199951,
        "genuineness": 4.406930446624756,
        "identity": 0.01987108588218689,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/6ff2ffc745db1b0681db6a125813b916d323025c875d1616698f630ca0a430a5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "701900f9e6b6731c42a9d69e8cb069d72b4e4de438510316b2757b9d71f11c6c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "db211f6d08d17f45cf37273f883ccf8ac7b66e31077fa8d6bb80a131015b9272",
      "generation_seconds_batch": 24.56245242897421,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 5.959072113037109,
        "genuineness": 3.886019229888916,
        "identity": 0.4682355523109436,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/701900f9e6b6731c42a9d69e8cb069d72b4e4de438510316b2757b9d71f11c6c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "70a6811deb5e46d6ca6fb50e593e092145c4a38b2be226bae15804b352bb7d08",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f9edeee868ee038a7257a317274b70b7aa1cbca12af173377807cb1223ef7a2a",
      "generation_seconds_batch": 24.33934889000375,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1866917610168457,
        "target_z": -0.06298822550492285,
        "ce": 6.252951145172119,
        "genuineness": 4.532451152801514,
        "identity": 0.4965025782585144,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/70a6811deb5e46d6ca6fb50e593e092145c4a38b2be226bae15804b352bb7d08.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "70b7e14cb93ec8b3b91699a9ccf5e6d8682b8cee223ded01e8e48c6f634c169d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "37bdbb441fbc4fe2a47d41088a71b16ce081211ad31b3cb82f79701654e36ec7",
      "generation_seconds_batch": 24.47622048202902,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 6.340320587158203,
        "genuineness": 4.457139015197754,
        "identity": 0.609622597694397,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/70b7e14cb93ec8b3b91699a9ccf5e6d8682b8cee223ded01e8e48c6f634c169d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "712e2dbf45863e8c4b25e9e13e2a3eb7d993dc85f7402eaba8f7a06ca591b6b5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b9175a7924963398c6562d5863f7a7ea8f555a1382ef9027fb9969fdf8f5ca40",
      "generation_seconds_batch": 24.410452560056,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 6.1020402908325195,
        "genuineness": 3.898571252822876,
        "identity": 0.39218708872795105,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/712e2dbf45863e8c4b25e9e13e2a3eb7d993dc85f7402eaba8f7a06ca591b6b5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "713293147b6c1ea71138d656e2c20b49b5a44f95fd256975caedf8dd9de4752b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d24b8f2686eca9dea9dabf35b3c20ab6e4d8240457ee168cedc9aac4f38fac2e",
      "generation_seconds_batch": 26.842566380044445,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.225412368774414,
        "target_z": -0.033203116940470775,
        "ce": 6.395919322967529,
        "genuineness": 4.168440818786621,
        "identity": 0.3823429346084595,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/713293147b6c1ea71138d656e2c20b49b5a44f95fd256975caedf8dd9de4752b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "71d967d47239512dcc61e3da6b4a5ffe16ff59cbbe2c63abe2f420ddfc2b6b85",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "98d3a0534d126c4aca5e79e0c1bda3850828f42893953d7d277200fba10a63c3",
      "generation_seconds_batch": 26.93076340202242,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7865447998046875,
        "target_z": 0.39843758668471435,
        "ce": 6.141753673553467,
        "genuineness": 3.9801597595214844,
        "identity": 0.32807326316833496,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/71d967d47239512dcc61e3da6b4a5ffe16ff59cbbe2c63abe2f420ddfc2b6b85.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "71db0798120498cb88480f0412a3b30694bec723003a5efb10e0245acf49c00e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "44904d6743e3fbac0ad35ad98f2cca5e3ce320bc7ec57735ea3d8157603263fb",
      "generation_seconds_batch": 20.918954427004792,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.771700143814087,
        "target_z": 1.1562500429841558,
        "ce": 6.507116317749023,
        "genuineness": 4.2249250411987305,
        "identity": 0.5056467056274414,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/71db0798120498cb88480f0412a3b30694bec723003a5efb10e0245acf49c00e.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "71ef26a69ca3510b25da9bb201f7d935bd2d2e212eb2f0a81ce31da4081d7d89",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "61e4543a57fa31c959fd49d1a993888aa84f3475d4012fb2f808162c8a49d501",
      "generation_seconds_batch": 23.863298756070435,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7662322521209717,
        "target_z": 0.3828125365365325,
        "ce": 6.324435234069824,
        "genuineness": 4.3881025314331055,
        "identity": 0.6538901925086975,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/71ef26a69ca3510b25da9bb201f7d935bd2d2e212eb2f0a81ce31da4081d7d89.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "720b3fb7910d30588b631f281f85040c0f2928251b75e656cbcd285a481ef091",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1571a05f4b6a2a32d9d33bfd471a77af79166f5d8fd619adaa08823e8496f0bf",
      "generation_seconds_batch": 26.682299426058307,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.695138454437256,
        "target_z": 0.32812495271742853,
        "ce": 6.427689552307129,
        "genuineness": 4.231201171875,
        "identity": 0.5675951242446899,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/720b3fb7910d30588b631f281f85040c0f2928251b75e656cbcd285a481ef091.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "727061dd2108f17d1ba5ba0e99ad5fbcffa064ff6fbbf5602e42636c0477453d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "484819b57f20b8ad2741df570e5a1aedc4ca78a7b380b2005ec2410b1d3dc8c6",
      "generation_seconds_batch": 18.31112974905409,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.162325620651245,
        "target_z": 0.6875000057312208,
        "ce": 6.268836498260498,
        "genuineness": 4.331617832183838,
        "identity": 0.6225981712341309,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/727061dd2108f17d1ba5ba0e99ad5fbcffa064ff6fbbf5602e42636c0477453d.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "72e27d79884e988da0533c2edf6336be2e09776af84ecf42c8e4705b91e5de9d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d22a460d2a60835f861fd9aa2e4450af4a56a88f3c820d4a8f3db4dfff3852f2",
      "generation_seconds_batch": 16.118326456053182,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6519744396209717,
        "target_z": 0.29492183577695774,
        "ce": 6.23706579208374,
        "genuineness": 4.507347106933594,
        "identity": 0.7330293655395508,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/72e27d79884e988da0533c2edf6336be2e09776af84ecf42c8e4705b91e5de9d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "739bf2e1b490a2b89c790b1203047621a93bb5b2946adfd629541af5d2e406d0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d9da4b1ec71a61a0e716db9d2c21799caea1023d4867da4c2a4f1de91d0baa58",
      "generation_seconds_batch": 24.723739272914827,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.857638359069824,
        "target_z": 0.45312498710475324,
        "ce": 5.990842819213867,
        "genuineness": 3.8420867919921875,
        "identity": 0.46164461970329285,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/739bf2e1b490a2b89c790b1203047621a93bb5b2946adfd629541af5d2e406d0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "73d3052981966998485eba50726502e06ff3eeccdc38e151c0692eae2e1eb1aa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f438066a6022398b292ece3311c3df02ce3a65b09001c47e3abb454c3180af9a",
      "generation_seconds_batch": 23.170147718978114,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.229123115539551,
        "genuineness": 3.5973212718963623,
        "identity": 0.4593856632709503,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/73d3052981966998485eba50726502e06ff3eeccdc38e151c0692eae2e1eb1aa.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "74541d5445d64f7e192723499a4566492891089af731f738c0136b9edaa52423",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f8cf4c08fdd4000cfd0713069d9f40747bd1a24aff216d81f145ecbd719ec592",
      "generation_seconds_batch": 25.521379378973506,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7662322521209717,
        "target_z": 0.3828125365365325,
        "ce": 6.372091293334961,
        "genuineness": 4.582659721374512,
        "identity": 0.5091059803962708,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/74541d5445d64f7e192723499a4566492891089af731f738c0136b9edaa52423.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "7475427cbfc522103cc1cd688d2db95964a718d7c91f94a607925bee94dd4e82",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8956a6548a67be03a2e2e7487e78a9f5e5a41d89f4de9d4f3fd60ee699f697f1",
      "generation_seconds_batch": 23.109849028056487,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.401876926422119,
        "target_z": 0.10253896748710543,
        "ce": 6.348263263702393,
        "genuineness": 4.507347106933594,
        "identity": 0.5358268022537231,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7475427cbfc522103cc1cd688d2db95964a718d7c91f94a607925bee94dd4e82.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "7505be900853503441c0f53f8460e38b535ab73f8698f1e51b4b51a3ea6b06e7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b6a209aaad10486ad7e87b0b2096843984b50eaef73720c5cbcc9fffdf290643",
      "generation_seconds_batch": 24.764511785004288,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.436544179916382,
        "target_z": 0.8984375408349481,
        "ce": 6.0146708488464355,
        "genuineness": 4.193545341491699,
        "identity": 0.7413396835327148,
        "hypothesis": "The trefet boat. He press de la vie fenêtre. Now regard ensemble what contiene?",
        "wer": 0.7894736842105263,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7505be900853503441c0f53f8460e38b535ab73f8698f1e51b4b51a3ea6b06e7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "753c7637805d3d6d70ebbbb0c3a00d4f04f2f130616eb695f485f53fdc795d30",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cfa72a188a9fd4518dbed5a565709ea39c2efb72c58d1eeba67e794593d9655b",
      "generation_seconds_batch": 24.880217383033596,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2994349002838135,
        "target_z": 0.7929687732830845,
        "ce": 6.395919322967529,
        "genuineness": 3.7793264389038086,
        "identity": 0.43757152557373047,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/753c7637805d3d6d70ebbbb0c3a00d4f04f2f130616eb695f485f53fdc795d30.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "75a1209e80b083296b53b12fdd5204cb94b367c179d59ed86ac7b78e155c1c52",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "06ebac7e311707c7a693d8d9c3994534bd478cb8a03f041f5d048ef483fcb4ee",
      "generation_seconds_batch": 27.743932296987623,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.924043655395508,
        "target_z": 1.2734374605978571,
        "ce": 5.982900142669678,
        "genuineness": 4.042920112609863,
        "identity": 0.547745943069458,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/75a1209e80b083296b53b12fdd5204cb94b367c179d59ed86ac7b78e155c1c52.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "769559b8e607360776031097115c3c41d03ee7c656b692accd585cead3f88928",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1328387d78725a021b8e9d35b3e16ac4071c793e8bb010c09c91dcf2a5b7f5ff",
      "generation_seconds_batch": 18.190327496966347,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.943576693534851,
        "target_z": -0.24999997707511687,
        "ce": 6.197352409362793,
        "genuineness": 4.262581825256348,
        "identity": 0.4721836447715759,
        "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/769559b8e607360776031097115c3c41d03ee7c656b692accd585cead3f88928.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "76ec3a0e8124b6c929b03ba30227380b485fa2c12b95289cea9e3c564e09f89e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b9f5a0ec8549049802074ff938eb3f7ce44b5e79588cacf213fade9f9405c598",
      "generation_seconds_batch": 22.651784418034367,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5910370349884033,
        "target_z": 0.24804686873147727,
        "ce": 6.09409761428833,
        "genuineness": 4.093128204345703,
        "identity": 0.5437427163124084,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/76ec3a0e8124b6c929b03ba30227380b485fa2c12b95289cea9e3c564e09f89e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "771ad446175aac8cb2244fbabd78083ee42fe22af55d64fded7ae30006aebf87",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4207f589cfa4a581d81498fa16ba382e1bbd4debd57a74806afe1bf04b7fa671",
      "generation_seconds_batch": 23.956173336016946,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.466623067855835,
        "target_z": 0.15234373459734415,
        "ce": 5.990842819213867,
        "genuineness": 4.532451152801514,
        "identity": 0.4130641222000122,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/771ad446175aac8cb2244fbabd78083ee42fe22af55d64fded7ae30006aebf87.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bd0b6fee609449d794a935ca37822045dce7cc872817f9c82e07c0ebf07f718f",
      "generation_seconds_batch": 18.07494239101652,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6287331581115723,
        "target_z": -0.49218752077567535,
        "ce": 6.24500846862793,
        "genuineness": 4.2374773025512695,
        "identity": 0.8109341859817505,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "7860d27745b5644de596604a2b270f627fc14306605646d8b2a9ca0455fa8c4c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c2eea479bf0c8c7865fa3dd538f0346f2b4612f097c945f47442592f1e5756c5",
      "generation_seconds_batch": 20.947430817061104,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 6.268836498260498,
        "genuineness": 4.306513786315918,
        "identity": 0.7626738548278809,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7860d27745b5644de596604a2b270f627fc14306605646d8b2a9ca0455fa8c4c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "78cbe3fdc62a486170018ed857b1d489f451501ceb8e648d9f78c1c9faab7bfb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4d9e2fcd59255f4169859a40f8b865765e38046685413e1348febb6ce6fa72ac",
      "generation_seconds_batch": 22.34501046105288,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.411543369293213,
        "target_z": 1.6484375637598312,
        "ce": 6.213237762451172,
        "genuineness": 4.137060642242432,
        "identity": 0.35919857025146484,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/78cbe3fdc62a486170018ed857b1d489f451501ceb8e648d9f78c1c9faab7bfb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "790ebaacf4a368dba4111a002054676f5ca61ce692e951a9e99e3341897923f5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "384884878aab235c79049a4a2cca18c4b6acac4ed9adce5d8fee7df9020d69e0",
      "generation_seconds_batch": 24.013965774909593,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6392791271209717,
        "target_z": 0.28515620235922723,
        "ce": 5.974957466125488,
        "genuineness": 3.7040140628814697,
        "identity": 0.46896907687187195,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/790ebaacf4a368dba4111a002054676f5ca61ce692e951a9e99e3341897923f5.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9a67467099ca3f44230085ed4b72f8dfc89e0ea3666f9cabd570d4de62d47486",
      "generation_seconds_batch": 17.222310820012353,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.157639026641846,
        "genuineness": 4.18099308013916,
        "identity": 0.7271410822868347,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "7951c6b3dc35871fef8f5563df3ef4772bc42ee661c7ed1c7292643bd3043870",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3291d1afa1e323bb5466c9baabc0b52812e7724c90b7c99375082ee572bf14d8",
      "generation_seconds_batch": 16.402796934940852,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 6.340320587158203,
        "genuineness": 3.9048471450805664,
        "identity": 0.36682575941085815,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7951c6b3dc35871fef8f5563df3ef4772bc42ee661c7ed1c7292643bd3043870.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "79acc6cfb0ff2f586310a00ee07997c28929f66db20bec0d3ed5bc45d0ee8bf7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "da87a1cd3945a28d343926999b16f960354c2dc0399f5abc279a29735b455a08",
      "generation_seconds_batch": 31.838294808985665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.822091579437256,
        "target_z": 0.4257812868947338,
        "ce": 6.197352409362793,
        "genuineness": 4.049196243286133,
        "identity": 0.2970483899116516,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/79acc6cfb0ff2f586310a00ee07997c28929f66db20bec0d3ed5bc45d0ee8bf7.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "79b448f11773a39da268b317282d5c1ed81a1244692b602ece5de357949d47b7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "42481a0ac3a9f73bca1553434c02c0da2164269f551f42cd0e1aa4419f7c405a",
      "generation_seconds_batch": 16.79419483698439,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0963101387023926,
        "target_z": 0.6367188219984611,
        "ce": 6.395919322967529,
        "genuineness": 4.118232727050781,
        "identity": 0.48561686277389526,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.",
        "wer": 0.08695652173913043,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/79b448f11773a39da268b317282d5c1ed81a1244692b602ece5de357949d47b7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "79fcad15d6dfde9fabe263917248ab84e9f91fbcbea1c5ffef19b48c6771ff50",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "631fecee29422c60344c1c2d2a7fd6e4e266502b53649c1c97cd324228276272",
      "generation_seconds_batch": 25.04858072393108,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.416231632232666,
        "target_z": 0.8828124906867663,
        "ce": 6.09409761428833,
        "genuineness": 3.785602569580078,
        "identity": 0.32997068762779236,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hin.",
        "wer": 0.0625,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/79fcad15d6dfde9fabe263917248ab84e9f91fbcbea1c5ffef19b48c6771ff50.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "7a4a5ee49ce959b1b617e1158916948e609e6c32695f2b6d08dc023286520df4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2500f1c789151772b38c4480308dd27bab9562abede89c054bb38a1832b03058",
      "generation_seconds_batch": 19.621911557973363,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.974824905395508,
        "target_z": 1.3124999942687792,
        "ce": 6.308549880981445,
        "genuineness": 3.8922953605651855,
        "identity": 0.3624453544616699,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7a4a5ee49ce959b1b617e1158916948e609e6c32695f2b6d08dc023286520df4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "7a68fde70cbb69d7493d782661b3326ecb5bd4c23d7b938a486dfbebaebb9cd9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "760f09ebaaedcbc19b388fa00329ec28aa06062181092d6cd16667cb1a9dc32e",
      "generation_seconds_batch": 24.988349049934186,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.433615207672119,
        "target_z": 0.12695305103143176,
        "ce": 6.2767791748046875,
        "genuineness": 4.080576419830322,
        "identity": 0.3520766496658325,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7a68fde70cbb69d7493d782661b3326ecb5bd4c23d7b938a486dfbebaebb9cd9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "7b2ff5217db8cf37ee645c2116ecb62c35d73465e8ca13f12cc363f944cbdd85",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2565cfce0ab59b26c624f4fe00e2f1013c171cd870623b1440242852e7403eb8",
      "generation_seconds_batch": 23.797777066007257,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4120333194732666,
        "target_z": 0.11035158426072891,
        "ce": 6.300607204437256,
        "genuineness": 4.6203155517578125,
        "identity": 0.5840796828269958,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7b2ff5217db8cf37ee645c2116ecb62c35d73465e8ca13f12cc363f944cbdd85.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "7b5ac135e0971613ac255665894df3bdd02afe4ac547100584970fa159806900",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "de1ae3ca2bc8af7a4a464d7275be3d684b6045c29a78a178a0d46aaad9cfedb5",
      "generation_seconds_batch": 25.203110423055477,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.959200859069824,
        "target_z": 0.5312500544465975,
        "ce": 6.229123115539551,
        "genuineness": 4.3504462242126465,
        "identity": 0.6304843425750732,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7b5ac135e0971613ac255665894df3bdd02afe4ac547100584970fa159806900.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "7ba3b5f73995877b4a33a0062f6f6392945544e9cd2064027bcc26c50627d8f0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ba205e2b3a7a4333c36159f9856ef17d44273654f825cd53906527a94c583627",
      "generation_seconds_batch": 25.15952368208673,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.353634834289551,
        "target_z": 0.06542963385935548,
        "ce": 6.324435234069824,
        "genuineness": 4.281409740447998,
        "identity": 0.7088861465454102,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7ba3b5f73995877b4a33a0062f6f6392945544e9cd2064027bcc26c50627d8f0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "7ba5e104e9bfc7bc7e153bac490d4df0bf252b1f1e2b9c610078827006d999ab",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c13501608ae033c364a5b5ca6e00599d8bb91b2b38356b893b5c665f31898acd",
      "generation_seconds_batch": 23.627084046020173,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.87795090675354,
        "target_z": 0.46875003725293507,
        "ce": 6.229123115539551,
        "genuineness": 4.030367851257324,
        "identity": 0.6006885766983032,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7ba5e104e9bfc7bc7e153bac490d4df0bf252b1f1e2b9c610078827006d999ab.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "7bed1a4449292ecdff586d577818d19e861746129a745715796793973e80bf5a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d2a2f38b629ed7881972a766e327b6367cf3f484185db182e40c313f54b42b8b",
      "generation_seconds_batch": 23.426741047063842,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2943568229675293,
        "target_z": 0.7890625565958053,
        "ce": 6.213237762451172,
        "genuineness": 4.281409740447998,
        "identity": 0.4556194841861725,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7bed1a4449292ecdff586d577818d19e861746129a745715796793973e80bf5a.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "7c04590c26ca0ea83c1d0625c2f90eb8c518d2c26263b128d2438c55e3e3abc9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "84ec9945b2a4750d6b46d2cbd254c8644a3c7de06ea9f16f47fa93bc1556ff0b",
      "generation_seconds_batch": 18.301854174002074,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6947487592697144,
        "target_z": -0.44140624534338313,
        "ce": 6.340320587158203,
        "genuineness": 3.998987913131714,
        "identity": 0.5779260396957397,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7c04590c26ca0ea83c1d0625c2f90eb8c518d2c26263b128d2438c55e3e3abc9.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "7d23bb7e69a5d16cc814cd701e92fbc50067ae7bcc9ca5d4a25be2b19b299d1a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5ff829b88f77ad001d474cdbf3a9dbc72e03ea6e46f38a9cab816fab578bbdc8",
      "generation_seconds_batch": 23.05104724492412,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.238107681274414,
        "target_z": -0.023437483522740245,
        "ce": 6.229123115539551,
        "genuineness": 4.049196243286133,
        "identity": 0.7465578317642212,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier, naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7d23bb7e69a5d16cc814cd701e92fbc50067ae7bcc9ca5d4a25be2b19b299d1a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "7db69a60bafa79e57602c4c31e417f33aa2c831b606548fd5cecbee7d87d147a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "015311ee2efe9bab8f102ed9b1373919ac6df6a47611e37d3d4f7ced8c39b0ac",
      "generation_seconds_batch": 23.732888206955977,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.260893821716309,
        "genuineness": 3.9801597595214844,
        "identity": 0.4889574944972992,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos.",
        "wer": 0.23529411764705882,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7db69a60bafa79e57602c4c31e417f33aa2c831b606548fd5cecbee7d87d147a.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "7eb7376e46eac3dc47321bf15defe69a505922b739df24997e44446bb8f5819b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ea78ed1ab9de9b849f7acb4bae548cbebd7bfa3cf602703a2d39ce73f66c02a0",
      "generation_seconds_batch": 14.978412685915828,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0121312141418457,
        "target_z": -0.19726568499871758,
        "ce": 6.41180419921875,
        "genuineness": 4.482243061065674,
        "identity": 0.5684722661972046,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7eb7376e46eac3dc47321bf15defe69a505922b739df24997e44446bb8f5819b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "7ec738de9a0dfa7def88f83f1495cfba78ac4e7171be713e7abf7318f9deda55",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5f614521c54a7385e8778f41f3fad6ad3620b4302f0648a4d021f9c64f813bf7",
      "generation_seconds_batch": 24.904970320058055,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7531471252441406,
        "target_z": -0.39648438664154223,
        "ce": 6.1894097328186035,
        "genuineness": 4.306513786315918,
        "identity": 0.6750839948654175,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7ec738de9a0dfa7def88f83f1495cfba78ac4e7171be713e7abf7318f9deda55.mp3"
    },
    {
      "id": "heldout-es-3",
      "language": "es",
      "sentences": [
        "Alguien ha movido la pequeña silla azul.",
        "Estaba aquí... junto a la estantería alta.",
        "La colocaremos después de comer."
      ],
      "text": "Alguien ha movido la pequeña silla azul. Estaba aquí... junto a la estantería alta. La colocaremos después de comer.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-3",
      "key": "7f4b23d588767335b2eae5e98e0266e66bf6f68d113478d18d3f9c473f4800ba",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La colocaremos después de comer.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fb4e354003796423e8ec850727126a2d739d601441f7bc8c4140a9d8e0745f1e",
      "generation_seconds_batch": 18.555340529885143,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7027556896209717,
        "target_z": 0.33398436944787985,
        "ce": 6.157639026641846,
        "genuineness": 4.337893962860107,
        "identity": 0.6172412037849426,
        "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comer.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7f4b23d588767335b2eae5e98e0266e66bf6f68d113478d18d3f9c473f4800ba.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The keys are on the kitchen table.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "65999b7e52f9b456779bb19aadbe2fa78f75792871d55636dddd5a00fd369e8b",
      "generation_seconds_batch": 17.605224541039206,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.5017801523208618,
        "target_z": -0.5898437632534481,
        "ce": 6.38003396987915,
        "genuineness": 4.281409740447998,
        "identity": 0.3574677109718323,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "7fde61de3fb99e54f06505c2b852b9e9c539e8b56c17e22c304032e3d4097a98",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3fa8390ad46d326032ee9cffaacff7d4b895454715ba8dcd71ecd830abf1051e",
      "generation_seconds_batch": 17.016234740032814,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.411153554916382,
        "target_z": 0.8789062739994871,
        "ce": 6.165581703186035,
        "genuineness": 4.319066047668457,
        "identity": 0.6570699214935303,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/7fde61de3fb99e54f06505c2b852b9e9c539e8b56c17e22c304032e3d4097a98.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "802c8411d4c9734287142e851444b1cfc79980ff6c6ac9c79f0db678699b7cea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a567e054a0d6694614c2f273e68609169ac87436030e94485b2e3fc2903d0ead",
      "generation_seconds_batch": 21.21289725706447,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8935749530792236,
        "target_z": 1.249999977075117,
        "ce": 6.006728172302246,
        "genuineness": 3.8546390533447266,
        "identity": 0.4869512915611267,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/802c8411d4c9734287142e851444b1cfc79980ff6c6ac9c79f0db678699b7cea.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d04970e8ca475eb16e44c0840d33dfa6faa69210758a4b72cc57cd6288bad1fc",
      "generation_seconds_batch": 18.63862544600852,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6261941194534302,
        "target_z": -0.49414062911931494,
        "ce": 6.316492557525635,
        "genuineness": 4.457139015197754,
        "identity": 0.5613473653793335,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.08695652173913043,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "82d84c8f89d8ef4fb971fdb0d92a1b6faa145f29635a7abef1cb07432105c6dc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1f830927f8476297d235f0e9a4efbde9db695fe9e6c496ce8959a30097e6910b",
      "generation_seconds_batch": 25.746281387051567,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.259199619293213,
        "target_z": 1.5312499627470648,
        "ce": 6.308549880981445,
        "genuineness": 4.256305694580078,
        "identity": 0.693885087966919,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/82d84c8f89d8ef4fb971fdb0d92a1b6faa145f29635a7abef1cb07432105c6dc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "83a622d32fa543add57ee1b36fde63039331d64c534647ace9f2d29c5ad82cf3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7656eddf9ea34497e6e28c84db5b2b997e1ffa5156e4cb839f57ad0e03ad05e7",
      "generation_seconds_batch": 18.190994561067782,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.82716965675354,
        "target_z": 0.42968750358201296,
        "ce": 6.141753673553467,
        "genuineness": 4.319066047668457,
        "identity": 0.5715665817260742,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/83a622d32fa543add57ee1b36fde63039331d64c534647ace9f2d29c5ad82cf3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "83dce889ef73e23f875f43355e831618f1a55d9a249c96bff8dd44d66a35a268",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "8f4ba3bc11d5a22063cee6d51a6b8011451c0b9c208ff67e67624bb7e7983ba3",
      "generation_seconds_batch": 17.97813995706383,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7310752868652344,
        "target_z": 1.1250001260868572,
        "ce": 6.24500846862793,
        "genuineness": 4.3127899169921875,
        "identity": 0.7373142838478088,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/83dce889ef73e23f875f43355e831618f1a55d9a249c96bff8dd44d66a35a268.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "8413daf0050032969140cb2097ce3d80196da834f68bbd3ef94c0455b2a7ce27",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fcd3d0ee84a2481b0f8bdcfa5ee7bfc82bc60b9e44eddf9139c096b0704a33e0",
      "generation_seconds_batch": 23.45672419492621,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2050998210906982,
        "target_z": -0.04882816708865263,
        "ce": 6.372091293334961,
        "genuineness": 3.8671910762786865,
        "identity": 0.2737017571926117,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8413daf0050032969140cb2097ce3d80196da834f68bbd3ef94c0455b2a7ce27.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "8449e345743aa47efdd7116ea9d6ccdfe21fc4386c44c4e25039e9b2f8be3c8e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e3596dee28c3f2c908434e1d10bb6cf972f64c281e9d222b6fab89e5c88a194b",
      "generation_seconds_batch": 17.519817364984192,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9388883113861084,
        "target_z": 0.5156250042984156,
        "ce": 6.054384231567383,
        "genuineness": 3.923675537109375,
        "identity": 0.4095107316970825,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8449e345743aa47efdd7116ea9d6ccdfe21fc4386c44c4e25039e9b2f8be3c8e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "845b0f5c962a2a39ecb68c52dd297c09a454c1ecb161effbdfc7aa7012a8d5c6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "27451d2f58337772f23286d735ff47a085cb37ac8adecc7fdca3e9f5d7b4e401",
      "generation_seconds_batch": 25.005990443984047,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4568567276000977,
        "target_z": 0.9140625909831299,
        "ce": 6.24500846862793,
        "genuineness": 3.7667744159698486,
        "identity": 0.3453735411167145,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/845b0f5c962a2a39ecb68c52dd297c09a454c1ecb161effbdfc7aa7012a8d5c6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "84698029878c5125ec7e7db5d0546c5641eb5aae450ca8dc561b1f20767fc9eb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "0c9377ffd314ff9b4721a53075305aa60ade61468a9cb95b0b9191363cce1c48",
      "generation_seconds_batch": 24.394059024984017,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4873251914978027,
        "target_z": 0.9374998911068051,
        "ce": 6.2767791748046875,
        "genuineness": 4.356721878051758,
        "identity": 0.6529586315155029,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/84698029878c5125ec7e7db5d0546c5641eb5aae450ca8dc561b1f20767fc9eb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "848a87573e31a2c1a27d1d1e65675b7cec19d527425975b5646fdaf7499fcfed",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "822ab88909d272166c12894f3c5f7ffb55b20741e8d5c0f2c4df99d8bd729f6a",
      "generation_seconds_batch": 22.562175465049222,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.53341817855835,
        "target_z": 1.7421874978507923,
        "ce": 5.903473377227783,
        "genuineness": 4.400654315948486,
        "identity": 0.5689355134963989,
        "hypothesis": "I've done the pet boat. It is pretty fenêtre. We will regard what.",
        "wer": 0.9473684210526315,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/848a87573e31a2c1a27d1d1e65675b7cec19d527425975b5646fdaf7499fcfed.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "84994dba0f900badeb9a31757d45a833b34750ee27dc6485f5aa228a3110bfde",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8e59595007e728eb158e11b4deef0d64a0b73c34d61566ed674a43c0e1d56824",
      "generation_seconds_batch": 27.743932296987623,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4517784118652344,
        "target_z": 0.9101561908967857,
        "ce": 6.054384231567383,
        "genuineness": 4.030367851257324,
        "identity": 0.23689350485801697,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/84994dba0f900badeb9a31757d45a833b34750ee27dc6485f5aa228a3110bfde.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "8559fb452ea64afd7bcbb6e9487fbb67930a438aff0309adbfa07345406ba45a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a1bce5bce45ec31943560d30a358120f945a60f74034a36291228e4c7d5a3d67",
      "generation_seconds_batch": 19.339650981943123,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9951374530792236,
        "target_z": 1.328125044416961,
        "ce": 6.09409761428833,
        "genuineness": 3.810706615447998,
        "identity": 0.6830365061759949,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8559fb452ea64afd7bcbb6e9487fbb67930a438aff0309adbfa07345406ba45a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "858d171c3045c9c7ff257d5df8073675be8ac0a8fc13a6a8c12f25365860b156",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c98b7ba4f001efb0cb03625994e7564294651ec6c51fd5c120fc8d6ea99359c8",
      "generation_seconds_batch": 23.28305400290992,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0912318229675293,
        "target_z": 0.6328124219121168,
        "ce": 6.268836498260498,
        "genuineness": 4.319066047668457,
        "identity": 0.3967374563217163,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/858d171c3045c9c7ff257d5df8073675be8ac0a8fc13a6a8c12f25365860b156.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "8607a3d4bd50e7fbc065524c839c92b3e9ac4e36a47717df1eb483c65c11f8d7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fcac2c6fbebdfa4e4e88d030645a4715f6820bc5443a65e593ab855f33f3d070",
      "generation_seconds_batch": 24.422291282913648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.208418369293213,
        "target_z": 1.4921874290761428,
        "ce": 6.2767791748046875,
        "genuineness": 4.21237325668335,
        "identity": 0.745570182800293,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8607a3d4bd50e7fbc065524c839c92b3e9ac4e36a47717df1eb483c65c11f8d7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "864d2fdadd0414181077030478fae173187dc528b8e848feba0df9439394fe44",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c62d699fcf6439cb471a714b94b0039a81a978e5b94dfba6603aa77bf96e888a",
      "generation_seconds_batch": 24.868275535991415,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 5.863759994506836,
        "genuineness": 3.9801597595214844,
        "identity": 0.5957729816436768,
        "hypothesis": "Gad staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/864d2fdadd0414181077030478fae173187dc528b8e848feba0df9439394fe44.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "86ea5a7bd69ad5a4602862c382574aefb6a9c9e1cac5f44185411d56b7543c8b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5deb94b221a4a51f3cbce99056caf9bc99217cd1db9b0b15a0060089a47024f2",
      "generation_seconds_batch": 29.124473108095117,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1674036979675293,
        "target_z": 0.6914062224185,
        "ce": 5.796247482299805,
        "genuineness": 4.017816066741943,
        "identity": 0.1509169638156891,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/86ea5a7bd69ad5a4602862c382574aefb6a9c9e1cac5f44185411d56b7543c8b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "8724c96d6169e44c077f0089fee6d7bce1f67a686afc2347c54141f483c6baca",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "e64c5cc7e0c8ec047a880c558ccc451f667146bd721bfa24a8cc45ade33db7ba",
      "generation_seconds_batch": 24.919410910923034,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0662312507629395,
        "target_z": 1.382812628236065,
        "ce": 5.879645347595215,
        "genuineness": 3.672633647918701,
        "identity": 0.28923577070236206,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abriendo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8724c96d6169e44c077f0089fee6d7bce1f67a686afc2347c54141f483c6baca.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "879069cd916fb84052e1cbd960447e95fc699ce25a2a242dda40ecbc86c47abb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6de6bcd474b508d362769295e4beff9dfc403ddd8a7dd60ba89ff10524ff88c",
      "generation_seconds_batch": 24.884573912015185,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0154500007629395,
        "target_z": 1.3437500945651428,
        "ce": 6.205295085906982,
        "genuineness": 4.061748504638672,
        "identity": 0.5582243204116821,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/879069cd916fb84052e1cbd960447e95fc699ce25a2a242dda40ecbc86c47abb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "87ba920e4b60ca7c68a9f81868f3db85fd7f5278fe6fb4340028b06ddd85ac7d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4c4dbf51c67044e78d85a354e3b9cd7c96560a231f9c29758aada8847ccb977b",
      "generation_seconds_batch": 24.46615599899087,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.90334153175354,
        "target_z": 0.48828130408839615,
        "ce": 6.046441555023193,
        "genuineness": 4.15588903427124,
        "identity": 0.283413290977478,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/87ba920e4b60ca7c68a9f81868f3db85fd7f5278fe6fb4340028b06ddd85ac7d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "883277e02471dc2508058d5c34ee7506d533500964989afbf116ad53051058e6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e6facd1874070fc66fda25e23eb2d960fdfeab1dcb16f6dd00b27981984c6a89",
      "generation_seconds_batch": 24.54459731699899,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.873262405395508,
        "target_z": 1.234374926926935,
        "ce": 5.80021858215332,
        "genuineness": 4.124508857727051,
        "identity": 0.15191753208637238,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/883277e02471dc2508058d5c34ee7506d533500964989afbf116ad53051058e6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "883c4fe9b1731930474f405ab5c18b0378948d1d9e8d4eae3a76c9aa26650e03",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4ce1641921fbb9e22db4c7eec0ca564e23b191de45485470aa539851add8aacb",
      "generation_seconds_batch": 18.190994561067782,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.366330146789551,
        "target_z": 0.075195267277086,
        "ce": 6.24500846862793,
        "genuineness": 4.218649387359619,
        "identity": 0.6713173389434814,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/883c4fe9b1731930474f405ab5c18b0378948d1d9e8d4eae3a76c9aa26650e03.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "885f2af90383c409e3339c18246d59cd509a27f69d09834fd012ba9f91679c67",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "d832503c165e0d32e068b1db5484121ecac55462d08bed4ad7860c0ef533e73c",
      "generation_seconds_batch": 21.21289725706447,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.320137023925781,
        "target_z": 1.5781249297925455,
        "ce": 6.022613525390625,
        "genuineness": 4.105680465698242,
        "identity": 0.5668821334838867,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/885f2af90383c409e3339c18246d59cd509a27f69d09834fd012ba9f91679c67.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "8874d7881567a409a6723f35ad4f7cd34736c0cb5dec9588b9fa0e066bb1fe1f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8017b3c2bb3dcf36051af8c427050ccae5562a95ed0aef5771bdaf6c98f2e9fb",
      "generation_seconds_batch": 24.54743218398653,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3451380729675293,
        "target_z": 0.8281250902667273,
        "ce": 6.340320587158203,
        "genuineness": 4.444586753845215,
        "identity": 0.4642876982688904,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8874d7881567a409a6723f35ad4f7cd34736c0cb5dec9588b9fa0e066bb1fe1f.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "889991d3b70e3101e7d935daa5c47078b19d5375f9d9b9f7d6202791fe8641d2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "086dd79291451d24d8e8c81f047362f789e88761c4a9954844c6f8e861e8443a",
      "generation_seconds_batch": 22.834648262010887,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4374239444732666,
        "target_z": 0.12988285109618997,
        "ce": 6.3641486167907715,
        "genuineness": 4.231201171875,
        "identity": 0.5065842866897583,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst!",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/889991d3b70e3101e7d935daa5c47078b19d5375f9d9b9f7d6202791fe8641d2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "88aa74132048ae90dc21e580c792384633263e3423b9cddace9d3660cba34dab",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "714db8f8fdf3427416a101b8c1e4c6e5d5e1baf7e3a188f560e1844be41fcaec",
      "generation_seconds_batch": 28.821310844970867,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4873251914978027,
        "target_z": 0.9374998911068051,
        "ce": 6.372091293334961,
        "genuineness": 3.798154592514038,
        "identity": 0.5338113903999329,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/88aa74132048ae90dc21e580c792384633263e3423b9cddace9d3660cba34dab.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "88b9a91d8b3d6d71b468c108dca63c3a03bfa4e4256ef6ea267328253b42d32d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c4ee3a547c557ad5d1db89dcbdc85a63ef81b8c73f7731b5e72c103810ddc645",
      "generation_seconds_batch": 16.604130673920736,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0912318229675293,
        "target_z": 0.6328124219121168,
        "ce": 6.070269584655762,
        "genuineness": 4.137060642242432,
        "identity": 0.42735517024993896,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/88b9a91d8b3d6d71b468c108dca63c3a03bfa4e4256ef6ea267328253b42d32d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "88e83cdf2b843df4c49fdeefffcd8b8b7c288b0b6ed5d4ff87594430771ced14",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5619dc0ca79d1e252167bdfae74bac3f09438c6db81fbaa7a4ca25c99efb3fa7",
      "generation_seconds_batch": 17.331806177971885,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0506069660186768,
        "target_z": 0.6015625050148182,
        "ce": 6.165581703186035,
        "genuineness": 4.3504462242126465,
        "identity": 0.5703260898590088,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/88e83cdf2b843df4c49fdeefffcd8b8b7c288b0b6ed5d4ff87594430771ced14.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "88f26fe3e20303a4b4a4c8a28d8ed3e232cebd5f83809542f247b9281badfbcc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cf2157de32b4bad5747f16a0687d4d6e4d5737deca7d9e64530247aff7b1a989",
      "generation_seconds_batch": 18.355277181020938,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2684175968170166,
        "target_z": -0.0001221437773476662,
        "ce": 6.141753673553467,
        "genuineness": 4.369274139404297,
        "identity": 0.6577144265174866,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/88f26fe3e20303a4b4a4c8a28d8ed3e232cebd5f83809542f247b9281badfbcc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "89327a39e8f43d18fc1d8b27fa59891ed6dc9d74332fd604e06244bfda958bfd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2f0fff24d254112a186dbe63b2b8145dc4914a5ea3cb46f89f8dfbc2e7fa5e68",
      "generation_seconds_batch": 18.190327496966347,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3117403984069824,
        "target_z": 0.033203116940470775,
        "ce": 6.229123115539551,
        "genuineness": 4.532451152801514,
        "identity": 0.47485244274139404,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/89327a39e8f43d18fc1d8b27fa59891ed6dc9d74332fd604e06244bfda958bfd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "8994e858adae791df31b44a534c37820c89882eda4987e4cd8756811a806d6b6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "6e46a86947cf1125704a5896fe1e3c0ca50200f7f8d20ea29c133d50606793e0",
      "generation_seconds_batch": 16.77721015899442,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.111544370651245,
        "target_z": 0.6484374720602987,
        "ce": 5.982900142669678,
        "genuineness": 3.9048471450805664,
        "identity": 0.356342077255249,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8994e858adae791df31b44a534c37820c89882eda4987e4cd8756811a806d6b6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "89a71ce76026c3245faaf04fbaf65d636aa3a8d395228e71b3f1444adf84c70c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3287fc3d6185ad0a495cd0ea3ce1092635d84d0aff44fe144a749ee483b2a42c",
      "generation_seconds_batch": 24.486056388006546,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.687521457672119,
        "target_z": 0.32226571938604226,
        "ce": 6.300607204437256,
        "genuineness": 4.005263805389404,
        "identity": 0.4064803719520569,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/89a71ce76026c3245faaf04fbaf65d636aa3a8d395228e71b3f1444adf84c70c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "8a0f1bdc4d5d5309ac91dfaf81dbcd1f68793e1d484195de51b96ccd3fba7c9e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "c49a1db99fa79cc5a0f9ea664e0e508608468bbeb5000ffde48bcfd291482884",
      "generation_seconds_batch": 24.47622048202902,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0252163410186768,
        "target_z": 0.5820312381793571,
        "ce": 6.173524379730225,
        "genuineness": 3.998987913131714,
        "identity": 0.3326222002506256,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8a0f1bdc4d5d5309ac91dfaf81dbcd1f68793e1d484195de51b96ccd3fba7c9e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "8a1cbab5c206a721a1d39231124fdff1b44b0c42df0210d49e1de11317676567",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1b660bc0d0fdc7b21d5a4a9d00d1418366758cc81027df25fe5bd90182121efe",
      "generation_seconds_batch": 22.94418328301981,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.4521684646606445,
        "target_z": 1.6796876640561949,
        "ce": 5.935244083404541,
        "genuineness": 3.7793264389038086,
        "identity": 0.4425138533115387,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8a1cbab5c206a721a1d39231124fdff1b44b0c42df0210d49e1de11317676567.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "8aaa4c268aafbe5bb2ed51db62fbe1c0f0f15b27152c07fcc164282fdd7c470a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3ac2f3b56f06492f02af29ef91c2dd5e0c19c0ad207ed69fb178aec0103f5601",
      "generation_seconds_batch": 23.844742977060378,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.44670033454895,
        "target_z": 0.9062499742095065,
        "ce": 6.1894097328186035,
        "genuineness": 4.287685871124268,
        "identity": 0.4825201630592346,
        "hypothesis": "I found the little box. That was beside the old window. We can look inside together.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8aaa4c268aafbe5bb2ed51db62fbe1c0f0f15b27152c07fcc164282fdd7c470a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "8af63c710f62946822c898d6cf379d7a969cde827378f85486020b919d77e0bf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "aa0765125b922827214b94de6730229c4edcaceb214989274eb2a495d27b23c5",
      "generation_seconds_batch": 24.594467393006198,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.497091770172119,
        "target_z": 0.17578121812008438,
        "ce": 6.078212261199951,
        "genuineness": 4.218649387359619,
        "identity": 0.6458241939544678,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8af63c710f62946822c898d6cf379d7a969cde827378f85486020b919d77e0bf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "8afc139b1b160f4e7f8c4769186816ba9024d0f3c10abfd8231b53301e692eb1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e046054a8ea3d962c0f3cd82d79d70d864b46c5637777c21bdc98d5f36c84c77",
      "generation_seconds_batch": 22.69549689500127,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.263887882232666,
        "target_z": 0.7656248896739999,
        "ce": 6.260893821716309,
        "genuineness": 4.168440818786621,
        "identity": 0.3100707232952118,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8afc139b1b160f4e7f8c4769186816ba9024d0f3c10abfd8231b53301e692eb1.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "8b4bfa61c9dfc1926af0090ccbad52933ebca1d65a7fa718c769e2f054c8f9c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3966f1d63bafeb7b910eadcb7a0f540dc8d350c5fa8b6dfb34c4a6ee28ecb308",
      "generation_seconds_batch": 20.668333042995073,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.872872829437256,
        "target_z": 0.46484382056565593,
        "ce": 6.165581703186035,
        "genuineness": 4.218649387359619,
        "identity": 0.7289232611656189,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lille le bien et verifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.09090909090909091,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8b4bfa61c9dfc1926af0090ccbad52933ebca1d65a7fa718c769e2f054c8f9c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "8b843ee9196b9b42853513cc739fa697c2a9612d9f2df46475cff62648a6b398",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4066ddcae415cfd46e2d1b98a9bec59463dfd343977c4289e5d7ddf82965f29b",
      "generation_seconds_batch": 23.639062172966078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.060763120651245,
        "target_z": 0.6093749383893766,
        "ce": 6.09409761428833,
        "genuineness": 4.519899368286133,
        "identity": 0.7474513053894043,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8b843ee9196b9b42853513cc739fa697c2a9612d9f2df46475cff62648a6b398.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "8b9382d5bcdd20410721220e2b7a6fea976263db7f84e31a2a59046194a91f1b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1190f6ca17b3df1ff02bfa3212e09d3c2c174721d6c0295d89bdb1ee27b112ed",
      "generation_seconds_batch": 24.367143192095682,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.187716245651245,
        "target_z": 0.7070312725666819,
        "ce": 6.141753673553467,
        "genuineness": 4.231201171875,
        "identity": 0.4274326264858246,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8b9382d5bcdd20410721220e2b7a6fea976263db7f84e31a2a59046194a91f1b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "8d45b795dff415d8775bce2921acc6bc6c0fb22f7682c81f9117f61c4964c6a3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "afa95de350cb16c8ae6a0737b4862bc85c37a5efcc468b100856cf822dbd7979",
      "generation_seconds_batch": 24.019897302030586,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9439663887023926,
        "target_z": 0.5195312209856948,
        "ce": 6.149696350097656,
        "genuineness": 3.7040140628814697,
        "identity": 0.36390331387519836,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8d45b795dff415d8775bce2921acc6bc6c0fb22f7682c81f9117f61c4964c6a3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "8d7ea835b021852fb27c5015987b05e7129e7c092e3d8bbcbfd47c60be728903",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "3ba92d0c6086d54248fa21f686f025486d870f2e9f1bf02556b582197ae38c7c",
      "generation_seconds_batch": 18.344505004002713,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.177949905395508,
        "target_z": 1.4687501289524676,
        "ce": 6.316492557525635,
        "genuineness": 4.2751336097717285,
        "identity": 0.4790093004703522,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8d7ea835b021852fb27c5015987b05e7129e7c092e3d8bbcbfd47c60be728903.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "8e029ab46c1012483aec00eac0f768eaaa03e3b5bcbb58474dd0b88284fffa67",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "8f4fc4cfb7fe1336b3e8a58e4489407f3bd7621d6963ae53a06890d939ad2814",
      "generation_seconds_batch": 24.337650311063044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.974824905395508,
        "target_z": 1.3124999942687792,
        "ce": 5.784333229064941,
        "genuineness": 3.773050308227539,
        "identity": 0.4067600667476654,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8e029ab46c1012483aec00eac0f768eaaa03e3b5bcbb58474dd0b88284fffa67.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "8e196ed0bcfaa284c00145be4f2cdd2e2a0a9ded4072ab8e93c1e2ecbb8d5250",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "49113cea8bdcc32b963938639b010811199f4a604df0c5ca55e09448f1e1d2ed",
      "generation_seconds_batch": 17.94874158699531,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 6.419747352600098,
        "genuineness": 4.394378662109375,
        "identity": 0.2997230291366577,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8e196ed0bcfaa284c00145be4f2cdd2e2a0a9ded4072ab8e93c1e2ecbb8d5250.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "8e3d822fe890ebaaabdcdf04a8109133303dfedfca74ca6f7a1d3707d5de3dfd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ea101676910583546d57c7dc9b5d72c2363357618d8db68114e15946d32fd8cf",
      "generation_seconds_batch": 24.120432006078772,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7789275646209717,
        "target_z": 0.39257816995426303,
        "ce": 6.205295085906982,
        "genuineness": 4.262581825256348,
        "identity": 0.6292227506637573,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8e3d822fe890ebaaabdcdf04a8109133303dfedfca74ca6f7a1d3707d5de3dfd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "8e62b81cf3225e8f0f27500dc962eddd8bfb2dc2fb9c45e648237c48844cc1e9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a0651a20172465a86cabd5f6764df459805ef5a8dd7ffc83915f529b96e7272c",
      "generation_seconds_batch": 22.80801281402819,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2533419132232666,
        "target_z": -0.011718833460902666,
        "ce": 6.324435234069824,
        "genuineness": 4.055472373962402,
        "identity": 0.6247717142105103,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8e62b81cf3225e8f0f27500dc962eddd8bfb2dc2fb9c45e648237c48844cc1e9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "8eabc4d92be59006e28000ca8013fc60f4a8c1d90cf68aba82ec5c18ab169dfb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9ee576b00851615ec8dab8e3a21a315bf64e4d999cbd3d81f7c5a21fb1c40f06",
      "generation_seconds_batch": 24.042632439988665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9896695613861084,
        "target_z": 0.5546875379693377,
        "ce": 6.459460258483887,
        "genuineness": 4.086852550506592,
        "identity": 0.34346914291381836,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8eabc4d92be59006e28000ca8013fc60f4a8c1d90cf68aba82ec5c18ab169dfb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "8f4dab666aa9813b8e307ae6b786dc98eaf963035aa53fd2aabceeb07f78e73c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "53b7d3e5df2c17d7b21a98b3304ac7fc377f366b7c8d1c953ae97c59666c7e91",
      "generation_seconds_batch": 16.232386863906868,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.401876926422119,
        "target_z": 0.10253896748710543,
        "ce": 6.260893821716309,
        "genuineness": 3.8295347690582275,
        "identity": 0.45004695653915405,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8f4dab666aa9813b8e307ae6b786dc98eaf963035aa53fd2aabceeb07f78e73c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "8f5b6825c2f187e2771dd4c833df625106118603d49e06488000f5c4b59ae201",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b21a013a0d4fbc9f6cfc4a4e18aeb4ae5fc1cf8d599cab5ab0fc5d9c95ac3791",
      "generation_seconds_batch": 23.538116502109915,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0912318229675293,
        "target_z": 0.6328124219121168,
        "ce": 6.173524379730225,
        "genuineness": 4.344170093536377,
        "identity": 0.30039918422698975,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8f5b6825c2f187e2771dd4c833df625106118603d49e06488000f5c4b59ae201.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "8f8ddcb41ccbe1070268a9846adb8027ab8df5ab81d5c32657e6d1b957a29089",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4c1c3706aa9521918dcbc79a125a996ffdf0a7ddf217205c1039bb73060b32d6",
      "generation_seconds_batch": 22.96646749402862,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.197352409362793,
        "genuineness": 4.061748504638672,
        "identity": 0.4735572338104248,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8f8ddcb41ccbe1070268a9846adb8027ab8df5ab81d5c32657e6d1b957a29089.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "8f92127fbf3478517319cd314329addffa19d09dbb48b590ca45be554d427fb5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "50d53c6d6849da76b9f696c8983a48c00a32d605ca582ec3abfb535aece24ed8",
      "generation_seconds_batch": 25.047236039070413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 6.292664527893066,
        "genuineness": 3.7667744159698486,
        "identity": 0.32525575160980225,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8f92127fbf3478517319cd314329addffa19d09dbb48b590ca45be554d427fb5.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "8fb3a613e8056f498e88271d7a62a885a4ee56c43effff99c1cdfa2f287aeeb7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3bc8c883a9df407daa57ced75039b4bfed1d8ae3a86265ded42103b27f8d33ba",
      "generation_seconds_batch": 17.712465291959234,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.643967628479004,
        "target_z": -0.48046868731477266,
        "ce": 6.3641486167907715,
        "genuineness": 4.482243061065674,
        "identity": 0.5602425932884216,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8fb3a613e8056f498e88271d7a62a885a4ee56c43effff99c1cdfa2f287aeeb7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "8fd8453db3d9a74c329abc357fb06ce9eb04026758d2ecf1f22e75f338263817",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d7d06069d5012f109e2775c7918fbdcf6571f3c47fe7c4bc840c1ad77091e791",
      "generation_seconds_batch": 27.290947637986392,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.85256028175354,
        "target_z": 0.44921877041747404,
        "ce": 6.054384231567383,
        "genuineness": 3.9550557136535645,
        "identity": 0.6917354464530945,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8fd8453db3d9a74c329abc357fb06ce9eb04026758d2ecf1f22e75f338263817.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "8fe23d3c8b349c244133269365f419a165487bab908c69633c5c5b9a0ad93a19",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e777c68491df42de8cd24487ac2abba50c89f44b89093a9ed0586f8a9626d72b",
      "generation_seconds_batch": 24.8765894069802,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 6.356205940246582,
        "genuineness": 4.218649387359619,
        "identity": 0.6623231172561646,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/8fe23d3c8b349c244133269365f419a165487bab908c69633c5c5b9a0ad93a19.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "903493af38c6e912a3bd1cacd449393cf9f8f9940d6fd00e98cee0b0eef51c00",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cb4082a42642a7d16cb70b8d12d30ed06972f30415df4673cb98e1068e8a940a",
      "generation_seconds_batch": 16.36079486995004,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.22668194770813,
        "target_z": -0.0322265169188847,
        "ce": 6.459460258483887,
        "genuineness": 4.300237655639648,
        "identity": 0.6197148561477661,
        "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/903493af38c6e912a3bd1cacd449393cf9f8f9940d6fd00e98cee0b0eef51c00.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "9065fbab2d9a08413c0bccbc52144bfedfc54def9ee0b89cb52309817afc3c9c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "94446d053a37796d6bd2fd6b5dcd8f133d2a8b3765664b73ed2f762da7ff0f15",
      "generation_seconds_batch": 18.820658784010448,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4310762882232666,
        "target_z": 0.1250000343873247,
        "ce": 6.403861999511719,
        "genuineness": 4.356721878051758,
        "identity": 0.45118215680122375,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave,",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9065fbab2d9a08413c0bccbc52144bfedfc54def9ee0b89cb52309817afc3c9c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "906f61585221d39ab4496a1626ca9f58f0d14f01ce7ea24f4ae42eb034aabb01",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "7360a57e502a9de49387a1bbb53ab26469b16e9a6dd1cfd279220ff51817afb9",
      "generation_seconds_batch": 18.342360563925467,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8297085762023926,
        "target_z": 0.43164052022612004,
        "ce": 6.284721851348877,
        "genuineness": 4.381826400756836,
        "identity": 0.4278157353401184,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/906f61585221d39ab4496a1626ca9f58f0d14f01ce7ea24f4ae42eb034aabb01.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "90ac190cc9af4699b0246d446f4298b1202e55b3bfcd3681bf62281696bcacd5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "987a11a93c6c5ada31d72b5ba7c2983732568a17dacd64772218932132c1620d",
      "generation_seconds_batch": 18.590096757980064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.09409761428833,
        "genuineness": 3.835810661315918,
        "identity": 0.5399364829063416,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/90ac190cc9af4699b0246d446f4298b1202e55b3bfcd3681bf62281696bcacd5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "91eeb07bc7909ef0884cf0f7b10ef0632e72810867aa415b3f091faf4f1eda8c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "3c3324b75c6f255e9f009f00c5ba3c3d24a992c84bfbaedbe32df1f10de1319c",
      "generation_seconds_batch": 24.502041860017926,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.205295085906982,
        "genuineness": 3.9801597595214844,
        "identity": 0.5319766998291016,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/91eeb07bc7909ef0884cf0f7b10ef0632e72810867aa415b3f091faf4f1eda8c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "921e5cee81b0eb55c6e667e2cb2c848fc4ca03626d3800a66153ab2dc46e11c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f760a2871a9d0078d3ddee4988a122d18a4de65f205347a100163931c838a571",
      "generation_seconds_batch": 24.804331645020284,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7920126914978027,
        "target_z": 1.1718750931323378,
        "ce": 5.879645347595215,
        "genuineness": 3.3368656635284424,
        "identity": 0.563896656036377,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/921e5cee81b0eb55c6e667e2cb2c848fc4ca03626d3800a66153ab2dc46e11c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "9221b9c0c3177430c14a209c48260812f149853d6da393f4eaf8710cd6c2a5f7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "ff35cf4b06f9fbdffab0098e566aeae8782439b1068612e36d9397e5921561c6",
      "generation_seconds_batch": 22.818959064083174,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.649825096130371,
        "target_z": 1.0624999254941299,
        "ce": 6.054384231567383,
        "genuineness": 3.9425034523010254,
        "identity": 0.5921112895011902,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen ingevallen.",
        "wer": 0.1111111111111111,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9221b9c0c3177430c14a209c48260812f149853d6da393f4eaf8710cd6c2a5f7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "923c56dad65378217a466ee7a316b0d8bdcb9273f5eb331876e3f884bd07d440",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "50bd5d2d4bcaf5bc9a10389e001cc577237715d7ba62015ef5b1756542055904",
      "generation_seconds_batch": 24.43924632598646,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.086543560028076,
        "target_z": 1.3984374949851819,
        "ce": 6.165581703186035,
        "genuineness": 4.337893962860107,
        "identity": 0.4975016713142395,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/923c56dad65378217a466ee7a316b0d8bdcb9273f5eb331876e3f884bd07d440.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "92c15f63fa7518e853d9a1c777dfbc6ecefb5e7345d57d402933e90328b0f10c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "be5aa433a155d5e25dae09fc8e9cd12043017b678ad3b3e2846407b102096674",
      "generation_seconds_batch": 23.831902164965868,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6291229724884033,
        "target_z": 0.27734376898466884,
        "ce": 6.229123115539551,
        "genuineness": 4.093128204345703,
        "identity": 0.6667847633361816,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/92c15f63fa7518e853d9a1c777dfbc6ecefb5e7345d57d402933e90328b0f10c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "92dcb1f39f6b4bd832282747f96c66fdaf185c8434c65251c240eb243de2c8ae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9115190e3ec3691ec7df811ca41843d5759976e019b898df170dde5ae4a5b5a9",
      "generation_seconds_batch": 16.74965383298695,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6592018604278564,
        "target_z": -0.46875003725293507,
        "ce": 6.300607204437256,
        "genuineness": 3.9173994064331055,
        "identity": 0.45549917221069336,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/92dcb1f39f6b4bd832282747f96c66fdaf185c8434c65251c240eb243de2c8ae.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "92f7d1fd33835595429cd4c59852e831925eaf36739d2ec5d6e810965c8562a2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "048d05aa51e5fb00a5ef52eac34320a4220c03b7ed252a1d6cdb880f1f182818",
      "generation_seconds_batch": 23.046598840039223,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8470923900604248,
        "target_z": -0.32421873603014933,
        "ce": 6.427689552307129,
        "genuineness": 4.193545341491699,
        "identity": 0.5044604539871216,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/92f7d1fd33835595429cd4c59852e831925eaf36739d2ec5d6e810965c8562a2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "933e68d5480d8a31cf456a7d670efd3506270545aae39f9b48ae2b5bab2c7106",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "67f11c4ce481826ff4ca712624794ac037daa4a47947540ca4c56c83b07b20d1",
      "generation_seconds_batch": 16.883477210067213,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7615437507629395,
        "target_z": 1.1484374262105324,
        "ce": 6.324435234069824,
        "genuineness": 4.111956596374512,
        "identity": 0.32669252157211304,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/933e68d5480d8a31cf456a7d670efd3506270545aae39f9b48ae2b5bab2c7106.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "93e3fef13d8893d3b4a9ea12d76a48fde3cc96082cd301f6e8b037c550428fd8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "927a9460653e89acd2350bc3af6c3eaaa5b3079d9b70dd4c1efac09cf1a1fef8",
      "generation_seconds_batch": 18.13812586606946,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.292664527893066,
        "genuineness": 3.8546390533447266,
        "identity": 0.2675088047981262,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/93e3fef13d8893d3b4a9ea12d76a48fde3cc96082cd301f6e8b037c550428fd8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "954256a00658fea4f3680a7f26156dd92ba75b94187a0039b746bf034e00ead0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6d6bdf34828ae4133b7bb40585fe30dc44a1f0b334f9a95c53a8b6f8eb22ac5f",
      "generation_seconds_batch": 24.33934889000375,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6092002391815186,
        "target_z": 1.0312500085968312,
        "ce": 6.062326908111572,
        "genuineness": 4.3127899169921875,
        "identity": 0.6110191345214844,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/954256a00658fea4f3680a7f26156dd92ba75b94187a0039b746bf034e00ead0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "959b9d44f9e8c74ae0f8cb0a7eeab1468cd4fa6b8d320a8c531129289c1f2adb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c717a9766665002e57f7efdcb929c758bb16cdc896480a81efcd3016a03cc23f",
      "generation_seconds_batch": 23.67621531302575,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.81447434425354,
        "target_z": 0.41992187016428245,
        "ce": 5.919358730316162,
        "genuineness": 4.218649387359619,
        "identity": 0.1935405731201172,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/959b9d44f9e8c74ae0f8cb0a7eeab1468cd4fa6b8d320a8c531129289c1f2adb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "95a44a19b837955dffd2a9211b157906169eeb6a8c58c245dea6f10588173811",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eff7ba58255c59afb4b9da9b86b5baba863e28d5e6b7a01a8a55c6b37bd60348",
      "generation_seconds_batch": 24.74157860199921,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.619356632232666,
        "target_z": 1.0390626253704547,
        "ce": 5.935244083404541,
        "genuineness": 4.268857479095459,
        "identity": -0.0046241432428359985,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/95a44a19b837955dffd2a9211b157906169eeb6a8c58c245dea6f10588173811.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "95b311e0b1a030b5d1f3503d6b2955c6841c27f7bb3fe0c3251c609aefd6bfcf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0eb2799e5d2abfafb8c74ab2d89f6ddbc35c3a7ee00d5070cee072583a1689cf",
      "generation_seconds_batch": 22.038111016037874,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.289278507232666,
        "target_z": 0.7851561565094609,
        "ce": 5.967014789581299,
        "genuineness": 4.293961524963379,
        "identity": 0.4994918406009674,
        "hypothesis": "De deur deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.05263157894736842,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/95b311e0b1a030b5d1f3503d6b2955c6841c27f7bb3fe0c3251c609aefd6bfcf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "96022a9f8a0793c76567f4e74df36d95dd156754f2773beada17044fe4bda28b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c9f7af033031cdc2c7c68f5d22cd7736881326538709a3b234118c0ba13f06ec",
      "generation_seconds_batch": 17.268889261060394,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8804898262023926,
        "target_z": 0.47070305389704215,
        "ce": 6.41180419921875,
        "genuineness": 4.331617832183838,
        "identity": 0.5183360576629639,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/96022a9f8a0793c76567f4e74df36d95dd156754f2773beada17044fe4bda28b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "961248e5c698300cd1d3a03ce6e93d29a0463fa333d346c0af1f89cd1a97898a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "3c2c72cfe1bc9450ef47f152734abe0144a9e34e675cd84e8bc2e965dc0371cf",
      "generation_seconds_batch": 17.953124103019945,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.695918083190918,
        "target_z": 1.8671875322381168,
        "ce": 5.990842819213867,
        "genuineness": 4.042920112609863,
        "identity": 0.5465173721313477,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/961248e5c698300cd1d3a03ce6e93d29a0463fa333d346c0af1f89cd1a97898a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "9647cf684729fabe89c0013f95a14f1e2fd445d33b8ac26d76be6fe9cf176646",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9ae45a8998b1a268b0e8fef7704a8564ecce48175557865921e56b5fa783480e",
      "generation_seconds_batch": 16.77721015899442,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 5.760505676269531,
        "genuineness": 4.13078498840332,
        "identity": 0.44211894273757935,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9647cf684729fabe89c0013f95a14f1e2fd445d33b8ac26d76be6fe9cf176646.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "96d78efdf73962c35302a454095c39cb18ae9bf4e1a031ee7ed68d04e91711a7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "b13c6bcc745d5c4871ee2bf88559442c90d5cff65e0e598849bc9c7a34bec8c9",
      "generation_seconds_batch": 24.31267366395332,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.536447286605835,
        "target_z": 0.20605471839486203,
        "ce": 6.157639026641846,
        "genuineness": 4.432034492492676,
        "identity": 0.5997376441955566,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/96d78efdf73962c35302a454095c39cb18ae9bf4e1a031ee7ed68d04e91711a7.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "971a21ea1f03e62bbfe7d1f512c076096f038302f97c162bca3a5a560a4a06bd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d2e5c4636a426a0d6893a9914ad5cd0b7c196745691eca37da76516c549f8c22",
      "generation_seconds_batch": 22.153304339037277,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.700606346130371,
        "target_z": 1.101562459165052,
        "ce": 6.268836498260498,
        "genuineness": 4.356721878051758,
        "identity": 0.7086960077285767,
        "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/971a21ea1f03e62bbfe7d1f512c076096f038302f97c162bca3a5a560a4a06bd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "978f2b3f60d623bf344f480531885aa81baad59b0939a37440f9276e88cba111",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "68f88e118623df40f42ed7e3a9bae13a89a241de49c58ec432408eb0d2cdd375",
      "generation_seconds_batch": 23.197913595009595,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 5.7684478759765625,
        "genuineness": 3.653805732727051,
        "identity": 0.47798293828964233,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/978f2b3f60d623bf344f480531885aa81baad59b0939a37440f9276e88cba111.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "97a432469d014cc501f7351753e7d34e7974f1ad32220f50d676d809f281a91d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eae2c8b0a427596f11a0ea27484f171a69535eccdd0dd444de09a35726ea32ca",
      "generation_seconds_batch": 18.51648142898921,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.060763120651245,
        "target_z": 0.6093749383893766,
        "ce": 6.157639026641846,
        "genuineness": 4.281409740447998,
        "identity": 0.40137502551078796,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/97a432469d014cc501f7351753e7d34e7974f1ad32220f50d676d809f281a91d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "97bee91214eb73dc6de932c996466e13e099b2ebac754508789febf1edcd7460",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9503d9cb7320f9874bd17875e82b729054d46076a3d886c9d1c15eacd7bd78d6",
      "generation_seconds_batch": 22.94418328301981,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5279502868652344,
        "target_z": 0.9687499914031689,
        "ce": 6.0305562019348145,
        "genuineness": 4.017816066741943,
        "identity": 0.315356582403183,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/97bee91214eb73dc6de932c996466e13e099b2ebac754508789febf1edcd7460.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "97c4855df79e0c7593a807073ebb09ae77cb806498799bc456e0041e79c628bd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7f6b602f4b6b123c17d5a1373d07c0d8226212b6c31f0e945f98fd8574b59ee8",
      "generation_seconds_batch": 18.26388685393613,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9388883113861084,
        "target_z": 0.5156250042984156,
        "ce": 6.260893821716309,
        "genuineness": 4.21237325668335,
        "identity": 0.6177622079849243,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/97c4855df79e0c7593a807073ebb09ae77cb806498799bc456e0041e79c628bd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "97c66bd0fd9b931eccf59d9b59ae175fc4b8d6021f3197aa743ea95e047a3bf6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "98f83500b5384bf0054855c9a2809a6e00d695bc43b887b1c7c36dadffe28864",
      "generation_seconds_batch": 24.34332014201209,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1435277462005615,
        "target_z": -0.09619134244539361,
        "ce": 6.268836498260498,
        "genuineness": 3.911123275756836,
        "identity": 0.24964748322963715,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/97c66bd0fd9b931eccf59d9b59ae175fc4b8d6021f3197aa743ea95e047a3bf6.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4a225699c4c77410657f8969f56287d3da259fa1594acf1f925451375e769d47",
      "generation_seconds_batch": 18.345194073976018,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1403539180755615,
        "target_z": -0.09863275079982625,
        "ce": 6.332377910614014,
        "genuineness": 4.369274139404297,
        "identity": 0.6553257703781128,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "99f1f4a12c45d594cf8a77d7e3392b4445bc5fd4d1726db4618c85208cfc4cfa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "11a0a856e052ad077cfef5caa8ea1c861717676b7db875956badd2b56ae15372",
      "generation_seconds_batch": 27.317600711015984,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.25842022895813,
        "target_z": -0.007812433374558387,
        "ce": 6.181467056274414,
        "genuineness": 4.394378662109375,
        "identity": 0.5695332884788513,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/99f1f4a12c45d594cf8a77d7e3392b4445bc5fd4d1726db4618c85208cfc4cfa.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "9ad2aa31743016c2c28173c1092989007333d1c9b007f9e907da323e81bacf8e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 133,
      "seconds_generated": 10.64,
      "mp3_sha256": "844328b08242e6c56dbc80de787487672e4228abfcd51f5ec33101a82ddcc50d",
      "generation_seconds_batch": 21.152613825979643,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 5.4779486656188965,
        "target_z": 2.468750037252935,
        "ce": 6.24500846862793,
        "genuineness": 4.369274139404297,
        "identity": 0.5272743701934814,
        "hypothesis": "J'ai trouvé la petite boîte. Elle is près de la vie fenêtre. We've regarded ensemble",
        "wer": 0.42105263157894735,
        "duration_error_s": 0.4400000000000013,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9ad2aa31743016c2c28173c1092989007333d1c9b007f9e907da323e81bacf8e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "9b01767c953722e41f0c7ab81328a3561cedf6cbd154b041e71ca7074f5b6ca8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bf4d111e52a7ce649e9eb2833e82db9116b86603dfe6b6bb24696c4308d09812",
      "generation_seconds_batch": 26.703512278036214,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.49748158454895,
        "target_z": 0.9453125078804285,
        "ce": 5.871703147888184,
        "genuineness": 4.068024158477783,
        "identity": 0.6611719727516174,
        "hypothesis": "De de staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.05263157894736842,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9b01767c953722e41f0c7ab81328a3561cedf6cbd154b041e71ca7074f5b6ca8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "9bed9a19d5b9df6ee98605785567a2e7870ff26ec12acc0be6dae19e34c1850f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0f766d1d45d7d14b41746b67728c903c7382f2d71e512d693f3a0e0245e6b6e9",
      "generation_seconds_batch": 24.97015704389196,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.898263454437256,
        "target_z": 0.48437508740111695,
        "ce": 6.340320587158203,
        "genuineness": 4.293961524963379,
        "identity": 0.4501236081123352,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9bed9a19d5b9df6ee98605785567a2e7870ff26ec12acc0be6dae19e34c1850f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "9c01c799640821830c2eab175a7ef964f165dbfe9c754c8cfab165ac0713ffa8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8896dcae9174164a82fc5591f832a6de039fab14e853a469b966a671ab609bad",
      "generation_seconds_batch": 24.46885795390699,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.934199810028076,
        "target_z": 1.2812498939724155,
        "ce": 5.927301406860352,
        "genuineness": 3.7793264389038086,
        "identity": 0.36062484979629517,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c01c799640821830c2eab175a7ef964f165dbfe9c754c8cfab165ac0713ffa8.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c7c74e097355a1cee24e956fe213d56cbd88ba2d7d6db197d11bbbd8fce367ec",
      "generation_seconds_batch": 18.21686824806966,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.928342342376709,
        "target_z": -0.261718718836487,
        "ce": 6.205295085906982,
        "genuineness": 4.444586753845215,
        "identity": 0.7878776788711548,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "9c1c2237f91fed4546b8083dba97bdcb5d24b271240a662dd2cdd1a7192bcb8f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "607057af1d7bcf58f4f413ad6a16f7f2f2de50503424841f24ee37f6409f2c12",
      "generation_seconds_batch": 29.124473108095117,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8931851387023926,
        "target_z": 0.48046868731477266,
        "ce": 5.990842819213867,
        "genuineness": 3.9801597595214844,
        "identity": 0.5129926204681396,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c1c2237f91fed4546b8083dba97bdcb5d24b271240a662dd2cdd1a7192bcb8f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "9c426c65dc46cf15931fdba316e4ce4e0c06a88ba24aa43d36c541946274bfbd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "da187ad9788989858a8fb771d7adbf90eb9a5b506e89c21476e9606c713fea41",
      "generation_seconds_batch": 25.521379378973506,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5402557849884033,
        "target_z": 0.20898433506055517,
        "ce": 6.229123115539551,
        "genuineness": 4.406930446624756,
        "identity": 0.45690011978149414,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c426c65dc46cf15931fdba316e4ce4e0c06a88ba24aa43d36c541946274bfbd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "9c758fdb5cf74910a3e02b7cbd77762a85d2bc573881d944a578a0e5eceddb02",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a521d709749bf8e80bdda3ad210d6ec510f494320f3b882106636cdb24687911",
      "generation_seconds_batch": 23.876020852010697,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1181371212005615,
        "target_z": -0.11572260928085466,
        "ce": 6.181467056274414,
        "genuineness": 3.948779582977295,
        "identity": 0.40175384283065796,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c758fdb5cf74910a3e02b7cbd77762a85d2bc573881d944a578a0e5eceddb02.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "85edad2ae703592c7b9df7c1dcb26548a34d5d9559696de80ce193a0ab9dded2",
      "generation_seconds_batch": 18.45528548490256,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4323458671569824,
        "target_z": 0.12597663440891077,
        "ce": 6.173524379730225,
        "genuineness": 4.2751336097717285,
        "identity": 0.5118528604507446,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "9ca527548eaf245b8d3af66c01b428a251d662047fc3ef638c752ac20fc5ebb9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "12278bbb0c6add71d2497b34fe5fde0d26fd5e8e3944081c14055aa3407daaa5",
      "generation_seconds_batch": 23.68723886902444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.157247543334961,
        "target_z": 0.6835937890439416,
        "ce": 6.316492557525635,
        "genuineness": 4.293961524963379,
        "identity": 0.5956676602363586,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9ca527548eaf245b8d3af66c01b428a251d662047fc3ef638c752ac20fc5ebb9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "9d08eb58c5e8ddb465183311c3eca4f7467f9d7a823f5c4ddd98fb5df6367246",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "75cf143e32277b804f7b86ce8c2d2b7a5d806c6fd9063f254c01e2fd9ad6b2ac",
      "generation_seconds_batch": 18.486398564069532,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.771700143814087,
        "target_z": 1.1562500429841558,
        "ce": 6.006728172302246,
        "genuineness": 3.8169827461242676,
        "identity": 0.4414582848548889,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready here.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9d08eb58c5e8ddb465183311c3eca4f7467f9d7a823f5c4ddd98fb5df6367246.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "9d3fb72cdd9dbf4756195adfcc2e011d4be96d8d9c8ddb5c8b59c43e6a214b9b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4da9ea1721c218105a8e290598690e393eb0846ea76c93b07130d046560b8ac9",
      "generation_seconds_batch": 25.190847465069965,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7535369396209717,
        "target_z": 0.37304690311880195,
        "ce": 6.395919322967529,
        "genuineness": 4.017816066741943,
        "identity": 0.3071407675743103,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9d3fb72cdd9dbf4756195adfcc2e011d4be96d8d9c8ddb5c8b59c43e6a214b9b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "9e34eb3405ad0adac9b5bc5e9310543aed3e479433e622a2eda264287acb6989",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8ef67be89e64c79572f793a15928ab01972b95329e01618734b68d56849741a0",
      "generation_seconds_batch": 24.713509969995357,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0459184646606445,
        "target_z": 1.367187394688818,
        "ce": 6.300607204437256,
        "genuineness": 3.6287014484405518,
        "identity": 0.3013167083263397,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9e34eb3405ad0adac9b5bc5e9310543aed3e479433e622a2eda264287acb6989.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "9e46616d86496614b69bc461ef32f6f22a8e4a6edf655964e411bc3cce1eb187",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5b9e867a15a1a64a4fc4fa070af4545eeaad658f72569c5569f90b2b5d39e8dc",
      "generation_seconds_batch": 18.486398564069532,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3299036026000977,
        "target_z": 0.8164062568058247,
        "ce": 6.054384231567383,
        "genuineness": 3.6349775791168213,
        "identity": 0.3645423352718353,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9e46616d86496614b69bc461ef32f6f22a8e4a6edf655964e411bc3cce1eb187.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "9e819a95bb64d8faa9f5c7f2263121da9dbef38cde8429ed7b6e685ea186fc89",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "46427e62c67160f393b649b730846f5436b3e9c800f3d9dd586721b6bd3d3093",
      "generation_seconds_batch": 17.92609799595084,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 6.141753673553467,
        "genuineness": 4.362998008728027,
        "identity": 0.4907349646091461,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9e819a95bb64d8faa9f5c7f2263121da9dbef38cde8429ed7b6e685ea186fc89.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "9f2a5febdf6072b6e7cffa69e4041762beed96f4c96b728a35ec3873a4558a93",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "38a6f672cf0c692ca5994fa140326b544a3858b7dc8b699b7bacd2fb4e121543",
      "generation_seconds_batch": 22.651784418034367,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1927943229675293,
        "target_z": 0.710937489253961,
        "ce": 6.086154937744141,
        "genuineness": 4.344170093536377,
        "identity": 0.6947181820869446,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9f2a5febdf6072b6e7cffa69e4041762beed96f4c96b728a35ec3873a4558a93.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "9f584da0eacc02d358706c7f300b73f34388d87f732051c15f71505a34cb0174",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "410b7f0f1784bb558072426f11ccc99feb0402ff408946824a05027bb054b46e",
      "generation_seconds_batch": 25.785818916978315,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5076379776000977,
        "target_z": 0.9531251246540521,
        "ce": 6.459460258483887,
        "genuineness": 4.218649387359619,
        "identity": 0.4579271376132965,
        "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9f584da0eacc02d358706c7f300b73f34388d87f732051c15f71505a34cb0174.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "9f92c8efc5ffc87708f1b5b618170849506c3966f77da2fd62dd4691f1c04ddf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d6d15323092d18081139d6707a662cdd1f53f26671812dc1a86f75d5e28c4c03",
      "generation_seconds_batch": 22.72521257097833,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.035762310028076,
        "target_z": 1.3593749613142596,
        "ce": 6.141753673553467,
        "genuineness": 3.973883628845215,
        "identity": 0.636559784412384,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/9f92c8efc5ffc87708f1b5b618170849506c3966f77da2fd62dd4691f1c04ddf.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "a03dc3672fa8b4289fa6bfbc7998f6cb84c648cf54042ad184ab90f963b341bf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "73893688d8514cd57eff63692ab398e7c231d7be62ce87466b945e8e25c82d47",
      "generation_seconds_batch": 22.462294909986667,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.771310329437256,
        "target_z": 0.3867187532238117,
        "ce": 6.292664527893066,
        "genuineness": 4.331617832183838,
        "identity": 0.5923388004302979,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a03dc3672fa8b4289fa6bfbc7998f6cb84c648cf54042ad184ab90f963b341bf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "a055bd8e4a2c234d4f3a7d0741d142aa929ac1279a22f76a54c9cf44e796099e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "64957b14bf3b3b4d2f429e6825c08e9edb5d1753d869c27bc8b14e0bff33ba0f",
      "generation_seconds_batch": 26.371254924917594,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.086153745651245,
        "target_z": 0.6289062052248376,
        "ce": 6.260893821716309,
        "genuineness": 4.406930446624756,
        "identity": 0.647650957107544,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a055bd8e4a2c234d4f3a7d0741d142aa929ac1279a22f76a54c9cf44e796099e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "a070ea969fd5b8a31c00cc2a61d0f582e7d27302b6fc33b909a04adb6c5c64a3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "4fa9e583961dc7d93fa0f19b2314d85c3bf06d967289e673dca48213e37f8d11",
      "generation_seconds_batch": 19.19931539101526,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.218574523925781,
        "target_z": 1.4999998624507012,
        "ce": 5.7684478759765625,
        "genuineness": 3.512594699859619,
        "identity": 0.30545493960380554,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a070ea969fd5b8a31c00cc2a61d0f582e7d27302b6fc33b909a04adb6c5c64a3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "a0d75b52abeb0fe47c844070bdcea7fe9e29ea56143149b15cd934241b94dc8e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7a7c18c6bb0d2a892dc76d447d66a8b7c5fd33c381df2728f499508150ece597",
      "generation_seconds_batch": 22.562175465049222,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.259199619293213,
        "target_z": 1.5312499627470648,
        "ce": 5.804190158843994,
        "genuineness": 4.2249250411987305,
        "identity": 0.5184187889099121,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contains.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a0d75b52abeb0fe47c844070bdcea7fe9e29ea56143149b15cd934241b94dc8e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "a0dcb5c0b1ae964bb8404d27df563dbc64b20f9803a8891bc63fcbdf83286c78",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7376452cd6d4196a814d94888dcb88ca1ecc20e92439caea6748410efbbb83c6",
      "generation_seconds_batch": 17.041742168017663,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.90334153175354,
        "target_z": 0.48828130408839615,
        "ce": 6.23706579208374,
        "genuineness": 4.293961524963379,
        "identity": 0.5347831845283508,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a0dcb5c0b1ae964bb8404d27df563dbc64b20f9803a8891bc63fcbdf83286c78.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "a13373fe651a92450ba803770914c970caa7e79fcfd716eeec681034ec09dfe1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "01acbc9dc75342c4ebfcdc632c89d467c56b1aad0d4218d4d18d6607bd444419",
      "generation_seconds_batch": 23.150213941000402,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.106856346130371,
        "target_z": 1.4140627285324288,
        "ce": 5.736677646636963,
        "genuineness": 3.747946262359619,
        "identity": 0.3419378995895386,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a13373fe651a92450ba803770914c970caa7e79fcfd716eeec681034ec09dfe1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "a14251d23e06ceed43f19925ffcdfd4dd2fcd13cf0e1c00e495b832921138786",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "05d08d32beaf4a53953fb896fbf58312823f2e457c2e384a8dd63861baa3ce42",
      "generation_seconds_batch": 17.94874158699531,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.898263454437256,
        "target_z": 0.48437508740111695,
        "ce": 6.395919322967529,
        "genuineness": 4.444586753845215,
        "identity": 0.40211939811706543,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a14251d23e06ceed43f19925ffcdfd4dd2fcd13cf0e1c00e495b832921138786.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "a20919a9ce4ee1ce8b12733c32af76ec34c1c95b4208fe5aab5e90dd72b7cc3d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "41434dec0cf761e31960d6d2b628e841f3d883dd494cfb832d61ad22c2231b27",
      "generation_seconds_batch": 24.166113131912425,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.056075096130371,
        "target_z": 1.3750001948615067,
        "ce": 6.229123115539551,
        "genuineness": 4.218649387359619,
        "identity": 0.8150546550750732,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a20919a9ce4ee1ce8b12733c32af76ec34c1c95b4208fe5aab5e90dd72b7cc3d.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "a246fb36182ca41814808b0cf9836776e7968b764cae210feccc1552e538a0b6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "65c51d32295832397128ca3dbc86a625173d8fa82896ade2fc195db0bd423037",
      "generation_seconds_batch": 17.712465291959234,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.801389217376709,
        "target_z": -0.35937505301379224,
        "ce": 6.395919322967529,
        "genuineness": 4.243753433227539,
        "identity": 0.42335784435272217,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a246fb36182ca41814808b0cf9836776e7968b764cae210feccc1552e538a0b6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "a2f677638666934ce2a0d10a464e22635549e4f263e17d14f1580294c84db1a9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "592ef1ceb2c5ac813fdecbdb8fce8c4b403748520bc77d183cdf3f54a45f5df4",
      "generation_seconds_batch": 24.907184681040235,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1784398555755615,
        "target_z": -0.06933585054663467,
        "ce": 6.221180438995361,
        "genuineness": 4.331617832183838,
        "identity": 0.4398232102394104,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a2f677638666934ce2a0d10a464e22635549e4f263e17d14f1580294c84db1a9.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "a34f9db73c39a0c5e489ea09a0df7222824ecbfd68633c9ce72a8990c4f87874",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e5275b637be7ae4d01da0a8ccf26c3d12f7fdc5df0cdd6f83871ba8be604991e",
      "generation_seconds_batch": 21.380664186086506,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.504709005355835,
        "target_z": 0.18164063485053572,
        "ce": 6.332377910614014,
        "genuineness": 3.7542223930358887,
        "identity": 0.41099071502685547,
        "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a34f9db73c39a0c5e489ea09a0df7222824ecbfd68633c9ce72a8990c4f87874.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "a3dcbfa27d8c3d1451e769d0865873e1f90dabf9d4dd3002409dc9c5bfabd6c5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 133,
      "seconds_generated": 10.64,
      "mp3_sha256": "19c7d28e785b3ba74e3f2dae8b1554609662b198f225b6ba08ff204f0f655f28",
      "generation_seconds_batch": 19.8482762289932,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 5.498397350311279,
        "genuineness": 3.5596652030944824,
        "identity": 0.5437338352203369,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo está.",
        "wer": 0.13333333333333333,
        "duration_error_s": 0.4400000000000013,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a3dcbfa27d8c3d1451e769d0865873e1f90dabf9d4dd3002409dc9c5bfabd6c5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "a3fb86207bd58f6c329169f3acd74488e11c76d24f1d995a99b1096c24fde2d7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "1e2faeed4efd8e86b79265b45f895aea9ad2674c1e5aaade2a593e5310224bc1",
      "generation_seconds_batch": 24.306299900985323,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3552942276000977,
        "target_z": 0.8359375236412857,
        "ce": 5.839932441711426,
        "genuineness": 3.810706615447998,
        "identity": 0.5233585834503174,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abriendo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a3fb86207bd58f6c329169f3acd74488e11c76d24f1d995a99b1096c24fde2d7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "a4a134e7553a016351dc980309ab5d919ef697d408dfddda9611c2396a757876",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a032824b967a792d52cefb658c4ae2461bc9944676df5ae3b789324892c8e3f2",
      "generation_seconds_batch": 17.980689401039854,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2241427898406982,
        "target_z": -0.03417971696205684,
        "ce": 6.2767791748046875,
        "genuineness": 4.507347106933594,
        "identity": 0.6855167746543884,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a4a134e7553a016351dc980309ab5d919ef697d408dfddda9611c2396a757876.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "a4aada164580650ab07b20563cb21b072bbd3afebbe37226e1dffaefe015eaa9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4f1ee4588d2d40251ef0c6b4e7f3c3cab5d6eb85acd0001433e3667179f14613",
      "generation_seconds_batch": 16.990720478002913,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.09972882270813,
        "target_z": -0.12988285109618997,
        "ce": 6.157639026641846,
        "genuineness": 4.432034492492676,
        "identity": 0.5332726240158081,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.09523809523809523,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a4aada164580650ab07b20563cb21b072bbd3afebbe37226e1dffaefe015eaa9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "a50b304c83b02d9a65d7bf5bf430f1e1b0f8cde8396a1ec2e05f7356ffd11375",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b6e1a380838da94e15bccf516f1f6deb66af62c6bad7e0aa0d504e43ced599d8",
      "generation_seconds_batch": 24.629874790087342,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.076387405395508,
        "target_z": 1.3906250616106235,
        "ce": 6.070269584655762,
        "genuineness": 4.168440818786621,
        "identity": 0.4766991436481476,
        "hypothesis": "J'ai trouvé la petite boîte littée près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a50b304c83b02d9a65d7bf5bf430f1e1b0f8cde8396a1ec2e05f7356ffd11375.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "a598c17a3fc0cc752df47367e562a8b8994dcaa595252f9c062c7ea0017e096d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f2c1060c7f449a926f3265b5a9566a284fbd7aab3ca42603c2fe6de26f2cc6a5",
      "generation_seconds_batch": 25.36313484807033,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.004903793334961,
        "target_z": 0.5664061880311753,
        "ce": 6.078212261199951,
        "genuineness": 3.9299514293670654,
        "identity": 0.3976074457168579,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a598c17a3fc0cc752df47367e562a8b8994dcaa595252f9c062c7ea0017e096d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "a5c633e4fff0726b3c5112183a1bf4ae1d4327aba1e21a0fd535e3467eeeaf10",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6e880fd5828bd1419538b053cd366b4d121298af1cf95b6a1f45bb47a74cb8f7",
      "generation_seconds_batch": 26.72725272795651,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.260893821716309,
        "genuineness": 3.9425034523010254,
        "identity": 0.4153934121131897,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a5c633e4fff0726b3c5112183a1bf4ae1d4327aba1e21a0fd535e3467eeeaf10.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "a5d7a5e2075d8f7a559a5f0bfdf613e65e89a95cc2c306d87cb60003e1c774b7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5ac5aff997c6efdc83eb8b9cb6e3f4637c78d9252af60261fd070e352e55df4c",
      "generation_seconds_batch": 23.28872497996781,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.543184757232666,
        "target_z": 0.9804688248640715,
        "ce": 6.070269584655762,
        "genuineness": 4.124508857727051,
        "identity": 0.5749152898788452,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a5d7a5e2075d8f7a559a5f0bfdf613e65e89a95cc2c306d87cb60003e1c774b7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "a615b7385d8e5554c4fd1d0b726a0a0de6a5b443eac136a9d9caee231a461d08",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "0174b755fbe5d33329a9287798b2f189ccbd5473c1af5081eb68db44c06e224d",
      "generation_seconds_batch": 17.980689401039854,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.05529522895813,
        "target_z": -0.16406256805824682,
        "ce": 6.252951145172119,
        "genuineness": 4.293961524963379,
        "identity": 0.7272025942802429,
        "hypothesis": "La porte et encore Eschumnitolange La Porte Ancor overte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.3333333333333333,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a615b7385d8e5554c4fd1d0b726a0a0de6a5b443eac136a9d9caee231a461d08.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "a62898d0aef3e1307d76c5c01ee5249c11c9427a5b46bf7636e168e413611d04",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a2b36bbd4fcdf753f8e9bc35068278777bb53e7f883f69779d07ee52d3939747",
      "generation_seconds_batch": 24.988349049934186,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.106466293334961,
        "target_z": 0.6445312553730195,
        "ce": 6.24500846862793,
        "genuineness": 3.9173994064331055,
        "identity": 0.3615916967391968,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a62898d0aef3e1307d76c5c01ee5249c11c9427a5b46bf7636e168e413611d04.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "a650bdbe55f8da4b7fc0841850d9148305a33938ffa1b3bd9dd7939b808402df",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "2b5c81871a4fff86b460c638e8d55a568f52196a33508501ef32bc59f30c4a44",
      "generation_seconds_batch": 17.323144803056493,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0252163410186768,
        "target_z": 0.5820312381793571,
        "ce": 6.205295085906982,
        "genuineness": 4.281409740447998,
        "identity": 0.46734344959259033,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a650bdbe55f8da4b7fc0841850d9148305a33938ffa1b3bd9dd7939b808402df.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "a68667682a413a42aee746b9cfb812bf12d22788faf2c4e2bdb51af0f957bc88",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "af4b80e42fa7deba6898d5a10102b00496ea1827149808bffedeccaf0d3b1e76",
      "generation_seconds_batch": 24.057538067921996,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.49748158454895,
        "target_z": 0.9453125078804285,
        "ce": 6.157639026641846,
        "genuineness": 3.8797430992126465,
        "identity": 0.4180268943309784,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a68667682a413a42aee746b9cfb812bf12d22788faf2c4e2bdb51af0f957bc88.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "a6e2e67b63a35a8e05f016cba4d466ebc469a518f36833857df5e79d597bb2da",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "39a71fc02df780f67eb535b7c3ffe945b928a90e915ffa7c7877e8381622ef6b",
      "generation_seconds_batch": 24.433534902054816,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5584189891815186,
        "target_z": 0.9921874749259091,
        "ce": 6.197352409362793,
        "genuineness": 4.13078498840332,
        "identity": 0.6294193267822266,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a6e2e67b63a35a8e05f016cba4d466ebc469a518f36833857df5e79d597bb2da.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "a71c0e090b33309b0b7c2323b721d43177ca190e42ba5b64ab66c2a4e6fdd42c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7c7b21477ef92da89b74a6c176a6e3d61b528de40997f82c1bced070c9d23b80",
      "generation_seconds_batch": 15.782711612991989,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3756065368652344,
        "target_z": 0.8515623903904025,
        "ce": 6.260893821716309,
        "genuineness": 4.287685871124268,
        "identity": 0.6086478233337402,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a71c0e090b33309b0b7c2323b721d43177ca190e42ba5b64ab66c2a4e6fdd42c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "a754b02d461870a7493b59397c5c36d5f1ecee1b26265ad1b4fa08ddb1e95498",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4a925b5aff50c3366d1c237f7cc141227040d0151543dfc2993fe78fd7dbdbf2",
      "generation_seconds_batch": 24.251674312050454,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.025606155395508,
        "target_z": 1.3515625279397012,
        "ce": 5.935244083404541,
        "genuineness": 3.6349775791168213,
        "identity": 0.35378456115722656,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a754b02d461870a7493b59397c5c36d5f1ecee1b26265ad1b4fa08ddb1e95498.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "a7adcd62e5992c143aab4d15e8786143fc89fbc51aa09df498f04dc72a1e1ad9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "8fee0c1cf79375adb3371352ada260efa51c01990af6476c52059c6fbbb14f60",
      "generation_seconds_batch": 24.78066837589722,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.58419942855835,
        "target_z": 1.7812500315217143,
        "ce": 6.24500846862793,
        "genuineness": 4.042920112609863,
        "identity": 0.4969283640384674,
        "hypothesis": "Encontrad la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay de la casa.",
        "wer": 0.29411764705882354,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a7adcd62e5992c143aab4d15e8786143fc89fbc51aa09df498f04dc72a1e1ad9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "a883195986f525f85fdcf70eb8662178a3dd165e0d544fe4e20fd49ee80aeea9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bdf45e6ec830ac6951256e87bff73f956bcffcb24d26080a8ade0587d662fff7",
      "generation_seconds_batch": 24.713509969995357,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.771700143814087,
        "target_z": 1.1562500429841558,
        "ce": 5.752562999725342,
        "genuineness": 3.5973212718963623,
        "identity": 0.4075559377670288,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a883195986f525f85fdcf70eb8662178a3dd165e0d544fe4e20fd49ee80aeea9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "a8b3a8ef38f90763691bea6cd917f0abad5298318c07959ea31a183932711908",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7a47b6f291875d42c22e0790b9397be70ad4f8f22026cf8b41a6186885b81ead",
      "generation_seconds_batch": 26.280428793048486,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9642789363861084,
        "target_z": 0.5351562711338766,
        "ce": 6.2767791748046875,
        "genuineness": 3.8044304847717285,
        "identity": 0.42353886365890503,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a8b3a8ef38f90763691bea6cd917f0abad5298318c07959ea31a183932711908.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b1df1a7cd228d5bafa0e6928aa459ef0b85bb61824b4b0a2d437c08ce9b33b28",
      "generation_seconds_batch": 18.169685131055303,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6211159229278564,
        "target_z": -0.49804693750612666,
        "ce": 6.09409761428833,
        "genuineness": 4.13078498840332,
        "identity": 0.4974935054779053,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "a934ee0d24ae1572c68348dc3943d0e937b432cbf9e70907e2abb707b2db7bc4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d1a7c82728062ede8abec648e3bc335700b76a01a44730433ba0d0faa5cc137c",
      "generation_seconds_batch": 17.816202211077325,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.543574333190918,
        "target_z": 1.7499999312253507,
        "ce": 6.038498878479004,
        "genuineness": 3.9801597595214844,
        "identity": 0.46018320322036743,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a934ee0d24ae1572c68348dc3943d0e937b432cbf9e70907e2abb707b2db7bc4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "a9446dac847d0c79550fb8a50cdf43718af40107490c3630432ef7e137cd27c3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d51f080b73ba70ab6310d3ea5788f6202023fd90d3bc08656b948ae48de794d0",
      "generation_seconds_batch": 24.97015704389196,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2537317276000977,
        "target_z": 0.7578124562994415,
        "ce": 6.356205940246582,
        "genuineness": 4.3504462242126465,
        "identity": 0.339474618434906,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a9446dac847d0c79550fb8a50cdf43718af40107490c3630432ef7e137cd27c3.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4e899975f187609ded58fc5db8bf8c8be83a9f72ba6f2d9a004857d7196d24fe",
      "generation_seconds_batch": 18.01340800698381,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.643967628479004,
        "target_z": -0.48046868731477266,
        "ce": 6.1894097328186035,
        "genuineness": 4.419482707977295,
        "identity": 0.7094497084617615,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "a9b84312c422a125613a6fe4deb1bc23ba53ff24d41031cffb79a9ae3453be80",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5617f216abf85c303301da13277161d6ef491af1c36e1b37da8e3d021d705d5e",
      "generation_seconds_batch": 23.844742977060378,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6595916748046875,
        "target_z": 0.3007812525074091,
        "ce": 6.395919322967529,
        "genuineness": 4.444586753845215,
        "identity": 0.5420091152191162,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/a9b84312c422a125613a6fe4deb1bc23ba53ff24d41031cffb79a9ae3453be80.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "aa2f49a4b686572ab4115c37d01d2327d162507d3cd890b0a71cabbcf1aa0717",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8de2a4e93c12fd6c12372cb9bf53e943bdc660abeae09515c7b7be6d908c8137",
      "generation_seconds_batch": 24.9069007729413,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1803441047668457,
        "target_z": -0.0678710422137881,
        "ce": 6.324435234069824,
        "genuineness": 4.243753433227539,
        "identity": 0.45422202348709106,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aa2f49a4b686572ab4115c37d01d2327d162507d3cd890b0a71cabbcf1aa0717.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "aa47ae56aebd09fdaa4f4dab66ca839422293cf245f0a103e94e3625b97c8ed4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9d0bd93d87d101828e0beeb0f94d77c6fb4c19b252a097b8aae9bc5a212985c8",
      "generation_seconds_batch": 25.267574862926267,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9994360208511353,
        "target_z": -0.20703122671691557,
        "ce": 6.23706579208374,
        "genuineness": 4.162164688110352,
        "identity": 0.6869231462478638,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aa47ae56aebd09fdaa4f4dab66ca839422293cf245f0a103e94e3625b97c8ed4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "aa815832c53f77e944e0c839064f95b964804d69a0155dca64ef56dba1588d4d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d89c69bea3646f5b9818c13b1f43aab2ec2666cbaaa9c5248ff6bed44d916026",
      "generation_seconds_batch": 18.26388685393613,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.467012882232666,
        "target_z": 0.9218750243576883,
        "ce": 6.24500846862793,
        "genuineness": 4.243753433227539,
        "identity": 0.5453463792800903,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aa815832c53f77e944e0c839064f95b964804d69a0155dca64ef56dba1588d4d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "aa965ba7a878cd0eaa32d878c8c408729784460ccdc3e50dbfe0419026930b74",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "461226d57d76cd2dde21bd78ba7c2c18f5c89a300bc2f49f11c3ba1ec87d1f73",
      "generation_seconds_batch": 18.153896252973936,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6037323474884033,
        "target_z": 0.2578125021492078,
        "ce": 6.205295085906982,
        "genuineness": 4.055472373962402,
        "identity": 0.18980540335178375,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aa965ba7a878cd0eaa32d878c8c408729784460ccdc3e50dbfe0419026930b74.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "aa9f1ffe71b8fbbc59aaed4d2c46dd2a74153d9c4e4c4deb7bd8289e35222ee1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0b5108efe31537a847cee952b660af97dace3b284321d1649ef5aa961c53e051",
      "generation_seconds_batch": 27.317600711015984,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2812716960906982,
        "target_z": 0.009765633417730527,
        "ce": 6.41180419921875,
        "genuineness": 4.262581825256348,
        "identity": 0.46884864568710327,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aa9f1ffe71b8fbbc59aaed4d2c46dd2a74153d9c4e4c4deb7bd8289e35222ee1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "aaef2e8b3ccd388007a4cd0d6e9a036d76df106380f42f4ddac0a5415e7a458f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2bfdb444cfe822b8209f8acf05e65c62088b6b2a1c29974139c4b47c3e03c028",
      "generation_seconds_batch": 24.54459731699899,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.885568141937256,
        "target_z": 0.47460945398338644,
        "ce": 5.863759994506836,
        "genuineness": 3.9927117824554443,
        "identity": 0.25969821214675903,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aaef2e8b3ccd388007a4cd0d6e9a036d76df106380f42f4ddac0a5415e7a458f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "aafd3eb77ac1805a4aab2518cd8d33fb2b3b2fe687de793eea716d91cab34d9e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "b025362ac2b905f579523e1dc065f5f28f01edbeb49054ec37a6264e330c1151",
      "generation_seconds_batch": 22.46797705197241,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2740442752838135,
        "target_z": 0.7734375064476234,
        "ce": 6.324435234069824,
        "genuineness": 3.948779582977295,
        "identity": 0.46314120292663574,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aafd3eb77ac1805a4aab2518cd8d33fb2b3b2fe687de793eea716d91cab34d9e.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "56fe7113ad2835135e55539d76a4f552efcf1e777cab0ecff059876f1a55e16f",
      "generation_seconds_batch": 18.406741626095027,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.0295149087905884,
        "target_z": -0.9531250329545196,
        "ce": 6.340320587158203,
        "genuineness": 4.042920112609863,
        "identity": 0.3101055920124054,
        "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "abd03d48f40b641c940f547460408593f4117205acd5822045d7321acdd2492a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fbe753317d0526e2522424b2784a78c28e1d89273ed8be52537816c6e3cf19b6",
      "generation_seconds_batch": 24.293049648054875,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.49748158454895,
        "target_z": 0.9453125078804285,
        "ce": 6.1894097328186035,
        "genuineness": 4.256305694580078,
        "identity": 0.639856219291687,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/abd03d48f40b641c940f547460408593f4117205acd5822045d7321acdd2492a.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "abdef1dd9e73a168dac419d457009c2b2525c0238d9a77d80b28a2a7cd7357df",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b77950f8c680eaf767b0b007c167a1ee444512ffb46d4a0f7d378cff41049494",
      "generation_seconds_batch": 24.68801408598665,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.44670033454895,
        "target_z": 0.9062499742095065,
        "ce": 6.507116317749023,
        "genuineness": 4.319066047668457,
        "identity": 0.24377383291721344,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/abdef1dd9e73a168dac419d457009c2b2525c0238d9a77d80b28a2a7cd7357df.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "abf772b307677c7df0bcfbf7872f0a6c5b1868cfc45266c020e3665fa7b0897c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "31f843197b94275642e1cdc1b3c55cc88d2052d7ae17104a857c226078887b55",
      "generation_seconds_batch": 18.82445190602448,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9131078720092773,
        "target_z": -0.27343755229738964,
        "ce": 5.982900142669678,
        "genuineness": 4.2374773025512695,
        "identity": 0.8119122982025146,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/abf772b307677c7df0bcfbf7872f0a6c5b1868cfc45266c020e3665fa7b0897c.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "ac710a508c4534a400c1c800093ee2696e28e42acc21bc99a934fea93bcdcc6d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c7b0a4f6a1a1363b0197028c222195a37f39f162d7e02011db8a8d252a4acd72",
      "generation_seconds_batch": 17.574932757066563,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2431857585906982,
        "target_z": -0.019531266835461053,
        "ce": 6.260893821716309,
        "genuineness": 4.3127899169921875,
        "identity": 0.577519416809082,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ac710a508c4534a400c1c800093ee2696e28e42acc21bc99a934fea93bcdcc6d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "ac96d611322994eb8b8b662d3dba0621007ec84b2aa5e6c431e7d66444cdb53f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5a4dc1456d19c3fe228a51e2c5d75200abe10daa86bb5747b531c92e3f972f89",
      "generation_seconds_batch": 24.669216251000762,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.933810234069824,
        "target_z": 0.5117187876111364,
        "ce": 6.268836498260498,
        "genuineness": 4.570107460021973,
        "identity": 0.7344546318054199,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ac96d611322994eb8b8b662d3dba0621007ec84b2aa5e6c431e7d66444cdb53f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "acf3852ee190229418fe94b6340ccd0b6c357a798a418a77d451c8ada4e58d20",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "44bafc2f7d2290caf001550df844438a097cada6d8f95b68bf44ff7fd7f15100",
      "generation_seconds_batch": 22.94981826399453,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0459184646606445,
        "target_z": 1.367187394688818,
        "ce": 6.157639026641846,
        "genuineness": 3.998987913131714,
        "identity": 0.31869393587112427,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/acf3852ee190229418fe94b6340ccd0b6c357a798a418a77d451c8ada4e58d20.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "ada280d05e5dfcb6a20b7fb19da2e5521b1bbc920f8aab5857544495f59289fa",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a2b1b53c39d9a8e27d93fa17102ab66d48000b7e5543a850d5d65a4db76edc29",
      "generation_seconds_batch": 24.425652467063628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7357635498046875,
        "target_z": 0.35937505301379224,
        "ce": 6.006728172302246,
        "genuineness": 4.168440818786621,
        "identity": 0.7572444677352905,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ada280d05e5dfcb6a20b7fb19da2e5521b1bbc920f8aab5857544495f59289fa.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "adac83147718c89b6f94f9570dff3c656ba75b1d59a6a81e8a94b52671f19492",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7ae49712502a8483dddfad39b5f1c3905f9a04884ddd22b68579701f5ffc179e",
      "generation_seconds_batch": 25.335343730053864,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.238887310028076,
        "target_z": 1.515625095997948,
        "ce": 6.0146708488464355,
        "genuineness": 4.074300289154053,
        "identity": 0.5262635350227356,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay de aquí?",
        "wer": 0.11764705882352941,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/adac83147718c89b6f94f9570dff3c656ba75b1d59a6a81e8a94b52671f19492.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "49fdb6a938f8ab518aa19341d2d76d834349a1770203a5d7b52dbfca62818091",
      "generation_seconds_batch": 19.066596223972738,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2685763835906982,
        "target_z": 0.0,
        "ce": 6.205295085906982,
        "genuineness": 4.356721878051758,
        "identity": 0.6096870303153992,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was, ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "adf9eb3d849923eaae8c3ed4e38cab95573b3295926a2de4184634f0baad762a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8b5b2a35cc0951c2afcde22925b0e64efc32445e38e79eeb68697a07edd1f022",
      "generation_seconds_batch": 24.54117157298606,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2994349002838135,
        "target_z": 0.7929687732830845,
        "ce": 6.1894097328186035,
        "genuineness": 3.911123275756836,
        "identity": 0.47020432353019714,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/adf9eb3d849923eaae8c3ed4e38cab95573b3295926a2de4184634f0baad762a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "ae07f4aeebc614acd92ce2f8de7227b11f67f67f728765b917e2e838d71ce074",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2b8a7a7bd6301693be6f0c38f88e981502ae15a6c52a1e2a4c291b69ab474ded",
      "generation_seconds_batch": 24.73036766902078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.670137643814087,
        "target_z": 1.0781249756423117,
        "ce": 6.332377910614014,
        "genuineness": 4.2249250411987305,
        "identity": 0.440541535615921,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ae07f4aeebc614acd92ce2f8de7227b11f67f67f728765b917e2e838d71ce074.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "ae0991f971ad4857cfda766c6968f8e060c23a36820ab9147bdc27443c7c41ed",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "27f32ee23aa48a76d58e21f85640efb810237a741358712dea53a763760c138b",
      "generation_seconds_batch": 24.03445187304169,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.624044895172119,
        "target_z": 0.27343755229738964,
        "ce": 6.1894097328186035,
        "genuineness": 4.036643981933594,
        "identity": 0.762557864189148,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ae0991f971ad4857cfda766c6968f8e060c23a36820ab9147bdc27443c7c41ed.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The road turns left behind the bridge.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1789e768f8c610ffaf4b531caff2d2724831a1c6fa48892c356b5e99308f4d8c",
      "generation_seconds_batch": 17.486787848058157,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.8670151233673096,
        "target_z": -1.0781249756423117,
        "ce": 6.403861999511719,
        "genuineness": 3.9299514293670654,
        "identity": 0.018926817923784256,
        "hypothesis": "The road turns left, behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "aeaa8ed0fb795eece363a6e5088aa6dbbd9ae8285c397356eeb38b47bc5e072c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a42fd7299f128a551fd91b43a1cdae5a3bbadf2d2c62585dad4cfac5c025e1c1",
      "generation_seconds_batch": 21.180299159954302,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6646697521209717,
        "target_z": 0.3046874691946883,
        "ce": 6.252951145172119,
        "genuineness": 4.162164688110352,
        "identity": 0.6147501468658447,
        "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aeaa8ed0fb795eece363a6e5088aa6dbbd9ae8285c397356eeb38b47bc5e072c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "aebc9d2e3246b04d7ad5c3ddad9b77260e85b787e2fbb46a005ab6dd3193d72a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "aa84a8bf384a981102705a5550f014c5941490f4a9c0af4407c8741f6c581775",
      "generation_seconds_batch": 25.012409711955115,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.682443141937256,
        "target_z": 0.318359319299698,
        "ce": 6.292664527893066,
        "genuineness": 4.331617832183838,
        "identity": 0.6724791526794434,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/aebc9d2e3246b04d7ad5c3ddad9b77260e85b787e2fbb46a005ab6dd3193d72a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "afabd81645d220db0180d7199b98294877b50c6efa062180a62622ffea76f98b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "968e096a1f26eaad9306edff095311a49bd8200f0d43b94292a1e27569c4cebd",
      "generation_seconds_batch": 25.21353465190623,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.771700143814087,
        "target_z": 1.1562500429841558,
        "ce": 6.09409761428833,
        "genuineness": 4.362998008728027,
        "identity": 0.6044274568557739,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/afabd81645d220db0180d7199b98294877b50c6efa062180a62622ffea76f98b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "afddae98c0ef40da34f1fe86df9c6af75814fe674fcc3de60f8113308e75c624",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "09ca58c95903cee417ec5c07c8d313c55d92fd25f9b0df9adc43f27558d9f3a4",
      "generation_seconds_batch": 24.032604067004286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.847482204437256,
        "target_z": 0.44531255373019485,
        "ce": 6.038498878479004,
        "genuineness": 4.362998008728027,
        "identity": 0.38033464550971985,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/afddae98c0ef40da34f1fe86df9c6af75814fe674fcc3de60f8113308e75c624.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "affb08aa6f2d3590994a6528ed8c6233ecc277d1ca45f8e4af372228492230bf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e05013975b60a6e09636d7e84325bacbab2de308a870c356644b1a153ad7129e",
      "generation_seconds_batch": 16.994527050992474,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.429806709289551,
        "target_z": 0.12402343436573864,
        "ce": 6.316492557525635,
        "genuineness": 4.325342178344727,
        "identity": 0.7696525454521179,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/affb08aa6f2d3590994a6528ed8c6233ecc277d1ca45f8e4af372228492230bf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b01011c1956e283e4fd9b8b682348cba4b0b6047c87e1f33050c51dd77e4069e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "30f01120643fb1ac195f77635babd4ffeefe87190a71bde1231cf4742dfa2b9d",
      "generation_seconds_batch": 25.015094945090823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.213237762451172,
        "genuineness": 4.457139015197754,
        "identity": 0.7280611395835876,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b01011c1956e283e4fd9b8b682348cba4b0b6047c87e1f33050c51dd77e4069e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b135bf32e4d6011b4054fc49beef075924fcb97607d0ffdad24f2b1965902da0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "21a65063e3a4b6f84ca5358a170ae5c9eb0de21e9d58a4c16f27b4fbd90a090d",
      "generation_seconds_batch": 22.217637603986077,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5326385498046875,
        "target_z": 0.20312491833010382,
        "ce": 6.070269584655762,
        "genuineness": 4.344170093536377,
        "identity": 0.6230936050415039,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b135bf32e4d6011b4054fc49beef075924fcb97607d0ffdad24f2b1965902da0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "b18dfd00ace2aee6c16a380bed51f980d00ddfa9b4ac2adc5fb19083c103d1ee",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "61edc2bb3709fb08d960193cf31d1c674b7be055a87f874c4d8622d1c50b5622",
      "generation_seconds_batch": 25.100550384027883,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1581273078918457,
        "target_z": -0.08496090069481653,
        "ce": 6.356205940246582,
        "genuineness": 4.15588903427124,
        "identity": 0.6147831678390503,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b18dfd00ace2aee6c16a380bed51f980d00ddfa9b4ac2adc5fb19083c103d1ee.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b33a8f8d2371d69d3106f6a09ee42681e038789680b3df0327775253932fe2c7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cab8e0d47c6de12759cc657c74de55800c0303dcb6309f093116bf14a6898183",
      "generation_seconds_batch": 18.417480968986638,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.205295085906982,
        "genuineness": 4.042920112609863,
        "identity": 0.43751460313796997,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b33a8f8d2371d69d3106f6a09ee42681e038789680b3df0327775253932fe2c7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "b358895ac345b6c93c71100b1060778094d12f35121f714cc8d31e60d6f85177",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1780418758202249221802616d23df3d928a27fe1afd930bb81186161c69499c",
      "generation_seconds_batch": 24.73036766902078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.80177903175354,
        "target_z": 0.41015623674655194,
        "ce": 6.23706579208374,
        "genuineness": 4.20609712600708,
        "identity": 0.5196535587310791,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b358895ac345b6c93c71100b1060778094d12f35121f714cc8d31e60d6f85177.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "b365d2705d6ce52d21297791cd6286292b446d2ff17cd28fc23722d6bff8c163",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6afc1ee162c6663467c2edeaadf724aba741e64387e803e3f548ef39f2eca2a2",
      "generation_seconds_batch": 23.28872497996781,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 5.967014789581299,
        "genuineness": 4.118232727050781,
        "identity": 0.6250773668289185,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b365d2705d6ce52d21297791cd6286292b446d2ff17cd28fc23722d6bff8c163.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "b3c81f7267bf324234628fc344707f38ff29a6039c97f811f7a260dabd4c02b8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2ca102bee60236d4f789de6f821de4d806561ab538200ff209d264aa83e99b4c",
      "generation_seconds_batch": 17.55791000497993,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.3849834203720093,
        "target_z": -0.6796874806571298,
        "ce": 6.2767791748046875,
        "genuineness": 4.3881025314331055,
        "identity": 0.4870753288269043,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b3c81f7267bf324234628fc344707f38ff29a6039c97f811f7a260dabd4c02b8.mp3"
    },
    {
      "id": "heldout-de-1",
      "language": "de",
      "sentences": [
        "Die Schlüssel liegen auf dem Küchentisch.",
        "Ich suchte in der Schublade... dann neben dem Fenster.",
        "Nimm sie mit, wenn du gehst."
      ],
      "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-1",
      "key": "b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8a3aa56b91f27cb63a84a4fd908b525fcb9014e310c7483d0e6a05492db4dfa2",
      "generation_seconds_batch": 16.539653074927628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.364670991897583,
        "target_z": -0.6953124391057792,
        "ce": 6.23706579208374,
        "genuineness": 4.306513786315918,
        "identity": 0.5314232110977173,
        "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "b4a1630fc729fb79b347f2a13703ef116928e9f9e236cdabfd9215dc198cb26d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0b66267e1286d1d3a2423c12729d336b11ad2250d308e2769cdf91b4551687c9",
      "generation_seconds_batch": 24.12866352405399,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3161838054656982,
        "target_z": 0.03662112531648947,
        "ce": 6.252951145172119,
        "genuineness": 4.099404335021973,
        "identity": 0.41608256101608276,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b4a1630fc729fb79b347f2a13703ef116928e9f9e236cdabfd9215dc198cb26d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "b55ce745566336024a00cb6171529206e7ade48d9f248b548ac04e63946c19f0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "91accf95d72b2c2b33a4a86ca8fef96971d12c68d2464eb0d407b60d436da506",
      "generation_seconds_batch": 23.574403621954843,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3959193229675293,
        "target_z": 0.8671876239376495,
        "ce": 6.109982967376709,
        "genuineness": 4.3504462242126465,
        "identity": 0.4666779935359955,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b55ce745566336024a00cb6171529206e7ade48d9f248b548ac04e63946c19f0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "b5c1734803973bcd93398dd56b41ad7622e2dfec27529ae087e5ef227a8cfca1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "29ba6cf77b3faa783725813e1325fa7700758af1df5cf37a53f73ecc448321e0",
      "generation_seconds_batch": 25.005990443984047,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.385762929916382,
        "target_z": 0.8593750071640259,
        "ce": 6.197352409362793,
        "genuineness": 3.5596652030944824,
        "identity": 0.305311381816864,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b5c1734803973bcd93398dd56b41ad7622e2dfec27529ae087e5ef227a8cfca1.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "b5cb235b77bf14aa016462a37a01572203b56f2a82608af09e2f2f6a6caded8b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ccade9486332bec2972c47dc63a0cfe4ea6da945f9335da6e77bf7ec93c86095",
      "generation_seconds_batch": 20.737932084011845,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4894745349884033,
        "target_z": 0.16992180138963306,
        "ce": 6.173524379730225,
        "genuineness": 4.15588903427124,
        "identity": 0.7938597202301025,
        "hypothesis": "Ik schreef het nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b5cb235b77bf14aa016462a37a01572203b56f2a82608af09e2f2f6a6caded8b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "b5e92158aa6ab7a3d4dbd3132fa75d59283a10a1acfd03e33b83d70ea863077d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "809bd25a5b33e22ba494b8ffbcc654011728fc504c8baaed8fab1db886870fb2",
      "generation_seconds_batch": 16.232386863906868,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6011931896209717,
        "target_z": 0.25585930210603564,
        "ce": 6.268836498260498,
        "genuineness": 3.8922953605651855,
        "identity": 0.47902485728263855,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b5e92158aa6ab7a3d4dbd3132fa75d59283a10a1acfd03e33b83d70ea863077d.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "b67d9b524370a79458ceffdd11ba65a3c00e680305c9cc9fd86e7f41ac2c2050",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6723fddfe9664eb2f4b99a05e51e00d418b5518390b1e5fc6089a28e700dee6f",
      "generation_seconds_batch": 16.448250198038295,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.522482395172119,
        "target_z": 0.19531248495554543,
        "ce": 6.3641486167907715,
        "genuineness": 4.218649387359619,
        "identity": 0.35618382692337036,
        "hypothesis": "Die Straße führ hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b67d9b524370a79458ceffdd11ba65a3c00e680305c9cc9fd86e7f41ac2c2050.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "b6fa4fe79d00d68801cb6e3c37723e83b1268b569210f00af61fc5ce0a29ebce",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "7d93daa34cc5c0e37ae4af8d9372b8ee1ed99e9c4539496c09ee6011e83a4526",
      "generation_seconds_batch": 16.39180539501831,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0506069660186768,
        "target_z": 0.6015625050148182,
        "ce": 6.324435234069824,
        "genuineness": 4.061748504638672,
        "identity": 0.4225667119026184,
        "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b6fa4fe79d00d68801cb6e3c37723e83b1268b569210f00af61fc5ce0a29ebce.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "b71d5ed669275de8cb019b8e17ec215a8a41bc26e5acb3f0ea13901d28e8d02f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "50498145177b394f5adea6d90bba42a9b1eef397736c9c224ee5b1912ed86c30",
      "generation_seconds_batch": 17.268889261060394,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.908419609069824,
        "target_z": 0.49218752077567535,
        "ce": 6.395919322967529,
        "genuineness": 4.457139015197754,
        "identity": 0.3989434838294983,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b71d5ed669275de8cb019b8e17ec215a8a41bc26e5acb3f0ea13901d28e8d02f.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "b731d59370f319aebfa06db9b953b6799fc372ef0c0b5cdee7c83cea4f6a50e3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f0d70e3592f12d9f8b8090aa912a0ffc7d4fad701c17c4a15f680d590c122453",
      "generation_seconds_batch": 25.785818916978315,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.598654270172119,
        "target_z": 0.2539062854619286,
        "ce": 6.316492557525635,
        "genuineness": 4.080576419830322,
        "identity": 0.49358755350112915,
        "hypothesis": "Someone moved the little blue chair. It used to stand here. Beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b731d59370f319aebfa06db9b953b6799fc372ef0c0b5cdee7c83cea4f6a50e3.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b75efe6f76a1de0315099fa5247ae431375b836e6eeff4de7a352696a644ae64",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "330dc6debff265439e40226c735b2fc94e7cd9ce59d981370f5fb8a139f1fd69",
      "generation_seconds_batch": 18.43203284207266,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4196505546569824,
        "target_z": 0.11621100099118024,
        "ce": 6.205295085906982,
        "genuineness": 4.124508857727051,
        "identity": 0.684921383857727,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b75efe6f76a1de0315099fa5247ae431375b836e6eeff4de7a352696a644ae64.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "b783efdedab2a1492f44a6044cca06e4b054fdff2c8da6122aab15ee1e303f77",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bd83324d23d85dc10cbbfaba26060c6b089fed8a8fe0f8a5ba67c8d06d40bd99",
      "generation_seconds_batch": 16.63328944996465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4120333194732666,
        "target_z": 0.11035158426072891,
        "ce": 6.038498878479004,
        "genuineness": 4.256305694580078,
        "identity": 0.6391111612319946,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b783efdedab2a1492f44a6044cca06e4b054fdff2c8da6122aab15ee1e303f77.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "b7841b467ecfec6c463c51669ba921230738042c3cf9f832775db82383dc5402",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5db8e34b78eb8edb910e3e3cb88238b33576b64e42515d34b9d63fa71e9035de",
      "generation_seconds_batch": 18.301854174002074,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4767792224884033,
        "target_z": 0.16015616797190252,
        "ce": 6.268836498260498,
        "genuineness": 4.218649387359619,
        "identity": 0.5730352401733398,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b7841b467ecfec6c463c51669ba921230738042c3cf9f832775db82383dc5402.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "b78ac118571f920c40a5211b28c94d5034c07027a33450f63e9811d132b55993",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "283b2c0c141ed63d50db996e84788f3b430155041aa25b1b633b92279da750d0",
      "generation_seconds_batch": 24.56245242897421,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6092002391815186,
        "target_z": 1.0312500085968312,
        "ce": 6.165581703186035,
        "genuineness": 3.6412534713745117,
        "identity": 0.3993528187274933,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b78ac118571f920c40a5211b28c94d5034c07027a33450f63e9811d132b55993.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "b7ba7cc314a1d86b36ee3096a9b961f738c9601fc2bd6e323430b96b742764c5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ad9f01e954af27033e73a023d28ae8f93c987435b388af822a716c6c398ae4d6",
      "generation_seconds_batch": 23.774076825007796,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8935749530792236,
        "target_z": 1.249999977075117,
        "ce": 6.125868320465088,
        "genuineness": 4.231201171875,
        "identity": 0.4369400143623352,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b7ba7cc314a1d86b36ee3096a9b961f738c9601fc2bd6e323430b96b742764c5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "b82aa90c1560e662381c0b3eb2c54c8d1b291b313132b8d7153b4edaee4217c5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "aea206fe8d3e2c5f1c3a653cb7cfbc3d2843e3853ef7c564feef50b00157498d",
      "generation_seconds_batch": 17.706117892055772,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1013882160186768,
        "target_z": 0.6406250386857403,
        "ce": 6.229123115539551,
        "genuineness": 4.268857479095459,
        "identity": 0.4336901307106018,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b82aa90c1560e662381c0b3eb2c54c8d1b291b313132b8d7153b4edaee4217c5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "b87ac04d2b34c35f2a343ed121d6c815c6c25d2e031f61f78cf6f6588f944a4b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b3358268460904b5342afcaee2f4a3b6cbf3e0caec278e832c9f451c86fddde4",
      "generation_seconds_batch": 18.75116862100549,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.934199810028076,
        "target_z": 1.2812498939724155,
        "ce": 6.149696350097656,
        "genuineness": 4.074300289154053,
        "identity": 0.45905429124832153,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b87ac04d2b34c35f2a343ed121d6c815c6c25d2e031f61f78cf6f6588f944a4b.mp3"
    },
    {
      "id": "heldout-de-0",
      "language": "de",
      "sentences": [
        "Deine Nachricht kam, als ich schon weg war.",
        "Ich las sie zweimal... dann legte ich das Handy weg.",
        "Sag mir, wann wir reden können."
      ],
      "text": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal... dann legte ich das Handy weg. Sag mir, wann wir reden können.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-0",
      "key": "b87bfe53f6f084a929d21a470d001120ede45e38d4113b6991c28ea0b1785753",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "af2a850dd26f968cfa7ed5699ea220798d915d1d3d9cee48e1a78ee3e9bd218f",
      "generation_seconds_batch": 16.35636682494078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3451380729675293,
        "target_z": 0.8281250902667273,
        "ce": 6.38003396987915,
        "genuineness": 4.645420074462891,
        "identity": 0.4677006006240845,
        "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b87bfe53f6f084a929d21a470d001120ede45e38d4113b6991c28ea0b1785753.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b898823cf7e53ba13b2e212549c1b1a89a39c6d0b294ae5e737c0bf6b3960342",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1120c21c833aadf598269f0260e50e4d3e15e75cfb833d45f438ad15ca664191",
      "generation_seconds_batch": 22.586942248046398,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7412314414978027,
        "target_z": 1.1328125594614156,
        "ce": 5.959072113037109,
        "genuineness": 3.911123275756836,
        "identity": 0.4381375014781952,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b898823cf7e53ba13b2e212549c1b1a89a39c6d0b294ae5e737c0bf6b3960342.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "b8bd71a6978b4cf164f753ba9a56e90d10e8c9f4e28b80e576cc2ce7e0723e78",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0428e49a7aff8bc30fbd56e20049f41393ef9026c1627167749e62cc858ef2be",
      "generation_seconds_batch": 16.883477210067213,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.85256028175354,
        "target_z": 0.44921877041747404,
        "ce": 6.308549880981445,
        "genuineness": 4.319066047668457,
        "identity": 0.4720756411552429,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b8bd71a6978b4cf164f753ba9a56e90d10e8c9f4e28b80e576cc2ce7e0723e78.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "b8d5c6c73bd11453199aa2267750f4faced201333cdc46e24a2f6b47cda9372f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "ad9142bf6c17e48e9ebfac8ebd1f8d0729042673431edac150d1ebc752d01c8d",
      "generation_seconds_batch": 32.48298022907693,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0154500007629395,
        "target_z": 1.3437500945651428,
        "ce": 6.038498878479004,
        "genuineness": 3.6475296020507812,
        "identity": 0.27872103452682495,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b8d5c6c73bd11453199aa2267750f4faced201333cdc46e24a2f6b47cda9372f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "b8e94c24573da1ba45f584ebf8e7cdad36aa753d97382725259d3b180981cb34",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8b809b535d1e88f866c940d149b848688b714762c421e6604dac1cf92dcb1ec1",
      "generation_seconds_batch": 25.8522548309993,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2943568229675293,
        "target_z": 0.7890625565958053,
        "ce": 6.284721851348877,
        "genuineness": 4.268857479095459,
        "identity": 0.39021992683410645,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b8e94c24573da1ba45f584ebf8e7cdad36aa753d97382725259d3b180981cb34.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "b8fbe3513caa6ad016a297b53a0a6c6a028641cdf1cf483b5085dbbf1d8fd798",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7f141325541ad799b1716ea06121a0f64d55dbf8eda3cb61cdbd3cde9c26d922",
      "generation_seconds_batch": 22.275149006047286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0641820430755615,
        "target_z": -0.1572265513062094,
        "ce": 6.403861999511719,
        "genuineness": 4.005263805389404,
        "identity": 0.5070354342460632,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b8fbe3513caa6ad016a297b53a0a6c6a028641cdf1cf483b5085dbbf1d8fd798.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "b97b5ea1e2799382ce0463aedcd45be7ba584145ce58833cf5cbfe868286e176",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9e6f71517e71cf3ed7fecda1fdf43b647f0818468fce4b3722fd844e0306149e",
      "generation_seconds_batch": 16.672924345941283,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.649435520172119,
        "target_z": 0.2929688191328507,
        "ce": 6.141753673553467,
        "genuineness": 4.331617832183838,
        "identity": 0.6505271792411804,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b97b5ea1e2799382ce0463aedcd45be7ba584145ce58833cf5cbfe868286e176.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b985857a11fc339ac0b77a858205a6dd30074e66a56654494ac112375abeaf4c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d83c41db831203959113ea3224ad5b6ff449a380e7a9a36ed9f367230b97c9f2",
      "generation_seconds_batch": 24.786747078993358,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.269355773925781,
        "target_z": 1.5390623961216232,
        "ce": 6.340320587158203,
        "genuineness": 4.2374773025512695,
        "identity": 0.49683326482772827,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b985857a11fc339ac0b77a858205a6dd30074e66a56654494ac112375abeaf4c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "b9b51e75c7e1fcd3375948edcb658d0ae5ca38cd97a46b3ecdce0a98d5fab36d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "608eeeb1fac8bd02871077b3fbffc4c098318900043ac649506c0377e89d62a1",
      "generation_seconds_batch": 25.498132769949734,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2689661979675293,
        "target_z": 0.7695312897603442,
        "ce": 5.839932441711426,
        "genuineness": 3.6914620399475098,
        "identity": 0.36111459136009216,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b9b51e75c7e1fcd3375948edcb658d0ae5ca38cd97a46b3ecdce0a98d5fab36d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "b9cf7d0985110c0a7e2e6fba6e6ac169a5ffdc93ccd8cfeb12dd633dd254180c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e492512950b70b72a5daa015a03081239f9a147b95bf4ff72c60919ba89e0a3f",
      "generation_seconds_batch": 26.182251614052802,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.157637119293213,
        "target_z": 1.4531248954052207,
        "ce": 6.141753673553467,
        "genuineness": 4.2249250411987305,
        "identity": 0.6433707475662231,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était prêt de la vie fenêtre. We've regarded ensemble the calcantine.",
        "wer": 0.42105263157894735,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b9cf7d0985110c0a7e2e6fba6e6ac169a5ffdc93ccd8cfeb12dd633dd254180c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "b9d581ddf02f6beb1f93bde4d91925ab6a6589f79c730a39c308ec754db6b8a9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "678e2e723b0da5d4b473a4a7547932159cfa05d09a2b04d010182edffbf95956",
      "generation_seconds_batch": 24.33617350202985,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.670137643814087,
        "target_z": 1.0781249756423117,
        "ce": 6.038498878479004,
        "genuineness": 4.356721878051758,
        "identity": 0.5124680995941162,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/b9d581ddf02f6beb1f93bde4d91925ab6a6589f79c730a39c308ec754db6b8a9.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2628a87a0903fccfe39c034f220189e80ec7ac7c619e3219d8507bd95a629662",
      "generation_seconds_batch": 18.174324468011037,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4279024600982666,
        "target_z": 0.12255862603289207,
        "ce": 6.252951145172119,
        "genuineness": 4.319066047668457,
        "identity": 0.6126071214675903,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "baaad4b514e4b145f81e5d41afad1057dcbae9a36df55f3bd11480b806eb4230",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8414278e7e3cb9cf5d8cce7396dc3ebf13ddb149f9b9754f395099d5f8dc8857",
      "generation_seconds_batch": 27.672645198064856,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5127158164978027,
        "target_z": 0.9570311579422661,
        "ce": 6.221180438995361,
        "genuineness": 4.017816066741943,
        "identity": 0.4138777554035187,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/baaad4b514e4b145f81e5d41afad1057dcbae9a36df55f3bd11480b806eb4230.mp3"
    },
    {
      "id": "heldout-nl-2",
      "language": "nl",
      "sentences": [
        "De weg gaat linksaf na de brug.",
        "Loop verder... tot aan het kleine houten hek.",
        "Ik wacht aan de andere kant."
      ],
      "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-2",
      "key": "bad6eb9a1c80750f07aec3d3624079ff2e987c387cbf870535549f9a042ec646",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c07d6e90cf82f31a2936ce79ea5d35e2698937b6c8a6f24d30ccfa7baf454e02",
      "generation_seconds_batch": 21.180299159954302,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.730685234069824,
        "target_z": 0.35546865292744795,
        "ce": 6.205295085906982,
        "genuineness": 4.15588903427124,
        "identity": 0.7531269788742065,
        "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.",
        "wer": 0.047619047619047616,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bad6eb9a1c80750f07aec3d3624079ff2e987c387cbf870535549f9a042ec646.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "bb3015709dfccc52ed06c4b816d64ca2c376b29158d7f179621a5096559b15df",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d68763ccf72841ca83992272617ebc9b986a2605f3ac73c362fb584e4a137672",
      "generation_seconds_batch": 25.158286132034846,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6396689414978027,
        "target_z": 1.0546874921195715,
        "ce": 6.070269584655762,
        "genuineness": 4.162164688110352,
        "identity": 0.2775830328464508,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bb3015709dfccc52ed06c4b816d64ca2c376b29158d7f179621a5096559b15df.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "bbe2e1100b9e47303676d79a1529e35420c35a9d637f8ff18e4e8d01b9f931ee",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d14da032cbae13dfcd4505b4bc610cffda9daacc4d512167f0c4da784439b548",
      "generation_seconds_batch": 21.708112930995412,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.868574142456055,
        "target_z": 2.0,
        "ce": 6.149696350097656,
        "genuineness": 4.143336772918701,
        "identity": 0.49167442321777344,
        "hypothesis": "En que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de.",
        "wer": 0.17647058823529413,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bbe2e1100b9e47303676d79a1529e35420c35a9d637f8ff18e4e8d01b9f931ee.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "bbe750fdc56a34fe2fcb63225d05cdda3fd94fd37a7f63baaadea98c560337ea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "37fdc1bfb4076cd4baa18ba640bfc030ed09b90b18a5b1b603731bd17844d248",
      "generation_seconds_batch": 23.197913595009595,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9388883113861084,
        "target_z": 0.5156250042984156,
        "ce": 5.804190158843994,
        "genuineness": 3.5471129417419434,
        "identity": 0.35008713603019714,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bbe750fdc56a34fe2fcb63225d05cdda3fd94fd37a7f63baaadea98c560337ea.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "bc28895e3eb60d7ae2bd1d5295080d1abf403122a44d5aee1d635afc7deb29a1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "fe978c3eef290ddf4c119061072e3f08119baa46d156e0cbfe97b94ebddbaf02",
      "generation_seconds_batch": 24.595551479957066,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.309980869293213,
        "target_z": 1.570312496417987,
        "ce": 6.157639026641846,
        "genuineness": 3.9299514293670654,
        "identity": 0.4905070960521698,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bc28895e3eb60d7ae2bd1d5295080d1abf403122a44d5aee1d635afc7deb29a1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "bc378279debb9309501c345e60d98b4ef9dee755831bdfb8453b4c34c9f23e96",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "9d589a657d798b756423de5bbb22a5c483b0bfb2ac34bf6f77d83eca7abfd981",
      "generation_seconds_batch": 24.014875861932524,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6092002391815186,
        "target_z": 1.0312500085968312,
        "ce": 6.0305562019348145,
        "genuineness": 4.18726921081543,
        "identity": 0.2648068368434906,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bc378279debb9309501c345e60d98b4ef9dee755831bdfb8453b4c34c9f23e96.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "bc76c183064680486c30214e3bb91ba01cbdb81eb4ab730fa44e09b90e49c087",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fa35da354b3cb0d7a6392fa09785ee8f3ca55dd4d51dab876d3fabe944687c5d",
      "generation_seconds_batch": 23.426741047063842,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6418182849884033,
        "target_z": 0.28710940240239935,
        "ce": 6.252951145172119,
        "genuineness": 4.168440818786621,
        "identity": 0.4757492244243622,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bc76c183064680486c30214e3bb91ba01cbdb81eb4ab730fa44e09b90e49c087.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "bc8af5a13f7ec5b8d3a536124b6ac6ca6d19abb6dbffb86a5e3487e7126b21d0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9e23a3e951303f76a31465c75d49d0fca22e886b25835ca216afc9b2545afe1a",
      "generation_seconds_batch": 24.8765894069802,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4771690368652344,
        "target_z": 0.9296874577322467,
        "ce": 6.205295085906982,
        "genuineness": 4.13078498840332,
        "identity": 0.6948256492614746,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bc8af5a13f7ec5b8d3a536124b6ac6ca6d19abb6dbffb86a5e3487e7126b21d0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "bd03d12ea1f944d08befd018b34fd87ae0aeced4da9abfcf2573893e191b26c6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "629cd66420b97987b1f2973d50737afb088519b48fe7192cfa83c6deb541a921",
      "generation_seconds_batch": 20.062782611930743,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.165581703186035,
        "genuineness": 4.080576419830322,
        "identity": 0.4683384299278259,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bd03d12ea1f944d08befd018b34fd87ae0aeced4da9abfcf2573893e191b26c6.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "bd8d69cea8213638b13fc478e5b62212c0f03a02a5c33d9a4dcf03c3f68d3d34",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "167d78fc2f1c1f926ae450edc02a56c01fac5d2ad55149d7cbee20125463c275",
      "generation_seconds_batch": 20.554392135934904,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6900603771209717,
        "target_z": 0.32421873603014933,
        "ce": 6.38003396987915,
        "genuineness": 4.281409740447998,
        "identity": 0.34182417392730713,
        "hypothesis": "Someone moved the little blue chair. It used to stand here, beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bd8d69cea8213638b13fc478e5b62212c0f03a02a5c33d9a4dcf03c3f68d3d34.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "bdb9980c6862fc44f1d420722a0db83c7e8f0a28dba0bdd831c2c88b852bc2b9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bb90f4663b2ab604aaaece9c4df4dc206e4a7adf70e1abba088956491d0d489a",
      "generation_seconds_batch": 25.080600660992786,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.078212261199951,
        "genuineness": 4.093128204345703,
        "identity": 0.48344993591308594,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bdb9980c6862fc44f1d420722a0db83c7e8f0a28dba0bdd831c2c88b852bc2b9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "bdc8efb2de9606a74c1742a767d9fe1a26ccad12200a988d503c72be4be6133b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0c29520d4c38c59ef7e379b4aa9761636bc7ba228616e5cd1d31a35d4a2a271e",
      "generation_seconds_batch": 18.119162601069547,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.82716965675354,
        "target_z": 0.42968750358201296,
        "ce": 6.24500846862793,
        "genuineness": 4.519899368286133,
        "identity": 0.5259142518043518,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bdc8efb2de9606a74c1742a767d9fe1a26ccad12200a988d503c72be4be6133b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "bec008af773a3bbd8280d28b0c9ae03639477c202c626dd03a9023b566afbd27",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ffab85e48036fe84987a996e5e590aa2bade4508ada7a9f8d9318549c98e1f6f",
      "generation_seconds_batch": 22.80801281402819,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.549142599105835,
        "target_z": 0.21582035181259257,
        "ce": 6.1894097328186035,
        "genuineness": 4.15588903427124,
        "identity": 0.5349524617195129,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bec008af773a3bbd8280d28b0c9ae03639477c202c626dd03a9023b566afbd27.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "bf800ffa24e75d0f28e5c5cc2571c23de736e6ddce038a08ed823d9d973eea61",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "85056c10c44d2cfe50a4c104c2d9f9dcc261735da2f6f2b0e650c7611cdbff8c",
      "generation_seconds_batch": 22.59376187401358,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4196505546569824,
        "target_z": 0.11621100099118024,
        "ce": 5.808161735534668,
        "genuineness": 3.9927117824554443,
        "identity": 0.6317718029022217,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bf800ffa24e75d0f28e5c5cc2571c23de736e6ddce038a08ed823d9d973eea61.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "bfe53720462ea1e20a874ce092a66a9cdc9e8ec74e35e3c51e9a564f4548ea60",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "df618b18c490aa0858d5720bd0293aa66025c368a548634fa2ceff8bf3da78cc",
      "generation_seconds_batch": 25.498132769949734,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.751387596130371,
        "target_z": 1.140624992835974,
        "ce": 5.903473377227783,
        "genuineness": 3.8420867919921875,
        "identity": 0.3879915475845337,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bfe53720462ea1e20a874ce092a66a9cdc9e8ec74e35e3c51e9a564f4548ea60.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "bfe89cde850eeb18c9f0fe571ad8f50fa732d7540fc91e328971ca2c686b50c4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "bc9db5a44b4cd0268795b249130ac8d220f92a0d11fd3a5567fe8b155ae7c3b9",
      "generation_seconds_batch": 18.445254555903375,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1752660274505615,
        "target_z": -0.0717772589010673,
        "ce": 6.300607204437256,
        "genuineness": 4.149612903594971,
        "identity": 0.5355733036994934,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/bfe89cde850eeb18c9f0fe571ad8f50fa732d7540fc91e328971ca2c686b50c4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c00e8db7fa6664c3e17f3b951bd5a876e062e8271f66c79f9775a647a2a48cec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0c0f91fdc36823d741038805c67dd89ef8d2c5ba95302a6d2b3e8d6fd78bfe31",
      "generation_seconds_batch": 23.87702177593019,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.062326908111572,
        "genuineness": 4.281409740447998,
        "identity": 0.5663269758224487,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c00e8db7fa6664c3e17f3b951bd5a876e062e8271f66c79f9775a647a2a48cec.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "c02632056a5b605bc20ea5349fb15a0baccaf92f3605c6e99591c21463b73a7a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3084815cebd5abfeca9245674bacc34ee46da027252e655fa6dbceaac9ac56d0",
      "generation_seconds_batch": 25.37693586794194,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 5.974957466125488,
        "genuineness": 4.093128204345703,
        "identity": 0.21457494795322418,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c02632056a5b605bc20ea5349fb15a0baccaf92f3605c6e99591c21463b73a7a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "c058c4d55334e0219661caeb35fb9f34a4ba27864205bfd4c75c81fe5160f5e2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "21c6cf3a8ac4be1f1d7508f4d117fc9946f123011d7d42a6d1f453e0b37f3642",
      "generation_seconds_batch": 22.818959064083174,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.177949905395508,
        "target_z": 1.4687501289524676,
        "ce": 5.839932441711426,
        "genuineness": 4.105680465698242,
        "identity": 0.06263163685798645,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c058c4d55334e0219661caeb35fb9f34a4ba27864205bfd4c75c81fe5160f5e2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "c09e896a07099d60f11b1125f224a3e8b3a803a22c0b6b1dfe831f731b333345",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "7619ceef4e5f9b95387beace3e84ca43c13fb74c0e3375cf95d56e569c731609",
      "generation_seconds_batch": 22.054422570974566,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6599814891815186,
        "target_z": 1.0703125422677533,
        "ce": 5.685050010681152,
        "genuineness": 3.3368656635284424,
        "identity": 0.4712824523448944,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c09e896a07099d60f11b1125f224a3e8b3a803a22c0b6b1dfe831f731b333345.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "c0dfbdaeb99929c8ebc54e6c33d7f941b292d4ed181223357d8a1c4d6c43c423",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2aa3917f5fe930f0ee10206a68e5b8a3d10c9e20e2e71dc3047b9e01d276c978",
      "generation_seconds_batch": 25.042329836986028,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8427939414978027,
        "target_z": 1.21093762680326,
        "ce": 6.356205940246582,
        "genuineness": 4.118232727050781,
        "identity": 0.5924074649810791,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c0dfbdaeb99929c8ebc54e6c33d7f941b292d4ed181223357d8a1c4d6c43c423.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "c10ecbd4a82fe34407abc99b15140555f7db70ee9585215c26b59446333e9a4b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c7108966c6182bb13d3256489679327f524bbecc0049e1c1a20bb1993b81a5e2",
      "generation_seconds_batch": 29.307012178003788,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 6.062326908111572,
        "genuineness": 4.256305694580078,
        "identity": 0.5510640144348145,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c10ecbd4a82fe34407abc99b15140555f7db70ee9585215c26b59446333e9a4b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c12229250521cd16847aeffcbad47c37e2cf189f5f2f5c263db93a73615d3f04",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a2f9895d8b78614a75d2e3628c7d7759b63f1222c3fb6ede6e4ade2f91bb66e2",
      "generation_seconds_batch": 18.490725807962008,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.213237762451172,
        "genuineness": 4.218649387359619,
        "identity": 0.679250955581665,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c12229250521cd16847aeffcbad47c37e2cf189f5f2f5c263db93a73615d3f04.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "c14bda000003dea05374586d7f34ec93de7350a762842d9bc74c599900c0b048",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f4afc18d41d0154a41b069a362114c5a7eb84fbe9c331fc91e767044e95bd95a",
      "generation_seconds_batch": 24.76331339799799,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9185757637023926,
        "target_z": 0.49999995415023374,
        "ce": 6.41180419921875,
        "genuineness": 3.8546390533447266,
        "identity": 0.3539767861366272,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreiten.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c14bda000003dea05374586d7f34ec93de7350a762842d9bc74c599900c0b048.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c197a68693123c2070b12d3480a006efe69f2f43ed0e52f3ddc11cb2710f7cd9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "82ecc6c9dc239b68c4b96fded2c7072afb28fda16e17445638bc4fc9df357b41",
      "generation_seconds_batch": 17.953124103019945,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 6.308549880981445,
        "genuineness": 3.8797430992126465,
        "identity": 0.58360755443573,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c197a68693123c2070b12d3480a006efe69f2f43ed0e52f3ddc11cb2710f7cd9.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6809d18af6e59527d7c0f7941d04fdefcc9ab8647925aa0ea23a58196923d160",
      "generation_seconds_batch": 18.45528548490256,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7074440717697144,
        "target_z": -0.43164061192565256,
        "ce": 6.260893821716309,
        "genuineness": 4.369274139404297,
        "identity": 0.7025387287139893,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "c437d58137d086a1162afac57d24e5185fc3657662b66a1900eb503964341cf8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3d75dbc8710f67bb8a55ebaae54de023c131c43bae80ee8dcce4b3431a57e2c9",
      "generation_seconds_batch": 26.371254924917594,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.412667989730835,
        "target_z": 0.1108397925719894,
        "ce": 6.395919322967529,
        "genuineness": 4.162164688110352,
        "identity": 0.6523924469947815,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c437d58137d086a1162afac57d24e5185fc3657662b66a1900eb503964341cf8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "c459c16f005151b03f4edecadc4051202ae038b996b4f376268328492c11124c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "bd8168548cfe3219f9bd55b4a07416c1bd4c1e30c2621f25279dbbff364d07e4",
      "generation_seconds_batch": 24.191576206008904,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.162325620651245,
        "target_z": 0.6875000057312208,
        "ce": 6.181467056274414,
        "genuineness": 4.137060642242432,
        "identity": 0.458576500415802,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c459c16f005151b03f4edecadc4051202ae038b996b4f376268328492c11124c.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "71a6b60b551d52bed4e90b3fe38316ead2cd49e6d48bde16d61ca223abbb42ea",
      "generation_seconds_batch": 18.21686824806966,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.1463117599487305,
        "target_z": -0.8632812238513051,
        "ce": 6.125868320465088,
        "genuineness": 4.293961524963379,
        "identity": 0.7654457092285156,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "c4b4c3becb2bea85c7a8367ea5d9b83054c9d957913ba27837774932c72ade9c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5f934d8a0a825b4da0486b46dac6356fa8a67b643a94aa3fce8358e60ec049c5",
      "generation_seconds_batch": 15.765736300963908,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3066623210906982,
        "target_z": 0.02929690025319158,
        "ce": 6.260893821716309,
        "genuineness": 4.281409740447998,
        "identity": 0.5091035962104797,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c4b4c3becb2bea85c7a8367ea5d9b83054c9d957913ba27837774932c72ade9c.mp3"
    },
    {
      "id": "heldout-es-0",
      "language": "es",
      "sentences": [
        "Tu mensaje llegó después de que me fuera.",
        "Lo leí dos veces... y guardé el teléfono.",
        "Dime cuándo podemos hablar."
      ],
      "text": "Tu mensaje llegó después de que me fuera. Lo leí dos veces... y guardé el teléfono. Dime cuándo podemos hablar.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-0",
      "key": "c5275e70fd17db2f1a8443920887320f03269f1642903cefc34bf40a296c43b2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "32b7bf0a891bfbf745d0228373279b47dec79b606636e15d5f5eb126acb7535a",
      "generation_seconds_batch": 18.82445190602448,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4713114500045776,
        "target_z": -0.6132812467761883,
        "ce": 6.09409761428833,
        "genuineness": 4.017816066741943,
        "identity": 0.6455641984939575,
        "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c5275e70fd17db2f1a8443920887320f03269f1642903cefc34bf40a296c43b2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c559fbcbc65795216f33452ba5d5010c9a41025ed821755d4fae356b21cd82fb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "0bd5ceb5002b9ab2fb64052eaaabd54c5c1bfeb6a86a95717d63c7cb56d58491",
      "generation_seconds_batch": 25.310821790946648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.934199810028076,
        "target_z": 1.2812498939724155,
        "ce": 5.959072113037109,
        "genuineness": 3.760498285293579,
        "identity": 0.5944336652755737,
        "hypothesis": "En qué he encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.11764705882352941,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c559fbcbc65795216f33452ba5d5010c9a41025ed821755d4fae356b21cd82fb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "c596f5c0c20cd1246d1ebecf39c915c55577935de348f34995f3927df1f4919c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e8aafcf3b1afb9a1cd09dc00d12aeb64005f9c2efca803a20baaa8e45fd2c9ed",
      "generation_seconds_batch": 17.041742168017663,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.756075859069824,
        "target_z": 0.37499991976290903,
        "ce": 6.133810997009277,
        "genuineness": 4.2751336097717285,
        "identity": 0.7274006605148315,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c596f5c0c20cd1246d1ebecf39c915c55577935de348f34995f3927df1f4919c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "c5a36a5346ba3b0fb14930ef366d86c699ac1b4dcf8b17b853bb729b903acc8c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cae93a039d76e68a74af9f488182cd6e6b87b2e98c5e1b0897a30ec3bc884799",
      "generation_seconds_batch": 23.246184922987595,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.807636737823486,
        "target_z": 1.9531250329545196,
        "ce": 6.3641486167907715,
        "genuineness": 4.394378662109375,
        "identity": 0.28661367297172546,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c5a36a5346ba3b0fb14930ef366d86c699ac1b4dcf8b17b853bb729b903acc8c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "c5c630f6d758ae7203493464d7180491cbc351f93c6ebf036afc7f9667a62d82",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "012bcf6d6a95a4d7369cf85b118e1c41486936f205f07f08252ca2cace806481",
      "generation_seconds_batch": 24.496363488957286,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.756075859069824,
        "target_z": 0.37499991976290903,
        "ce": 6.173524379730225,
        "genuineness": 4.2751336097717285,
        "identity": 0.46903204917907715,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c5c630f6d758ae7203493464d7180491cbc351f93c6ebf036afc7f9667a62d82.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "c63b13caee9adb8640293e965eac15c29daa82c7422ecd81065cbaa9acbe679e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "218489b505c1191b814df2e5cd6faf023e02f5c9120701d6a2eebb415ea79ddb",
      "generation_seconds_batch": 24.411455484922044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.106856346130371,
        "target_z": 1.4140627285324288,
        "ce": 6.141753673553467,
        "genuineness": 4.080576419830322,
        "identity": 0.16247548162937164,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c63b13caee9adb8640293e965eac15c29daa82c7422ecd81065cbaa9acbe679e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "c64040344210a74cdfcb84f66de0ab94805896286383c6e128e7116eac1388e7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5ef6c3724070e4c2402ba7f444c099d7c669f934c65e075dcfa79f278d1332ef",
      "generation_seconds_batch": 18.417480968986638,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 5.927301406860352,
        "genuineness": 3.8546390533447266,
        "identity": 0.47556036710739136,
        "hypothesis": "The porte is encore overte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.16666666666666666,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c64040344210a74cdfcb84f66de0ab94805896286383c6e128e7116eac1388e7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "c65a1c13764971a202f9113da0dd0e8da28eb67044961f3167583f37d08834be",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4f3f7b40f81ca4b80c1c004f57913beb0ba0551a6f206de4b25a4f52e119c27c",
      "generation_seconds_batch": 23.431594421039335,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.314669132232666,
        "target_z": 0.804687423344922,
        "ce": 5.990842819213867,
        "genuineness": 3.8420867919921875,
        "identity": 0.33818745613098145,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c65a1c13764971a202f9113da0dd0e8da28eb67044961f3167583f37d08834be.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c66f17529280fcb9e866147aa684882c489d3eed9cb51d9ea7870779e77e6c9d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "d58f666214e870b02067ca0ae489d0f6c00e9c04b3b3edfbcb9298ede373b588",
      "generation_seconds_batch": 28.821310844970867,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.1982622146606445,
        "target_z": 1.4843749957015844,
        "ce": 5.967014789581299,
        "genuineness": 4.030367851257324,
        "identity": 0.3915979266166687,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c66f17529280fcb9e866147aa684882c489d3eed9cb51d9ea7870779e77e6c9d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "c71de25e9ddaceec0ef3fecc05ce80dba1673eec9b57300baea69f94b9f06314",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "af2c23fab260766265c9fab215ddfc9ab1a4e12018a742c920e7365b0f305796",
      "generation_seconds_batch": 25.37693586794194,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.706074237823486,
        "target_z": 1.8749999656126752,
        "ce": 6.2767791748046875,
        "genuineness": 4.18099308013916,
        "identity": 0.4635065197944641,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c71de25e9ddaceec0ef3fecc05ce80dba1673eec9b57300baea69f94b9f06314.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "c72b3e57f6d17ad340eb79bd343edf8eb7f20e1ed2a9e343c9cd480886d7e60a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8f4c814f69c371b5254aad81e6963521f6330686f0886210cc5684ff27caab31",
      "generation_seconds_batch": 23.67438012198545,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.127168655395508,
        "target_z": 1.4296875952815455,
        "ce": 6.125868320465088,
        "genuineness": 4.055472373962402,
        "identity": 0.5098928809165955,
        "hypothesis": "The porte is encouraged. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.2222222222222222,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c72b3e57f6d17ad340eb79bd343edf8eb7f20e1ed2a9e343c9cd480886d7e60a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "c777be39346e81687f038967916155c54c47f843333386ac9188e30463dc90d6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ae1c047319cae0db5c33e13876e557592033a5e5edb8665530c232a5bbf5cb9f",
      "generation_seconds_batch": 23.28305400290992,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.385762929916382,
        "target_z": 0.8593750071640259,
        "ce": 6.38797664642334,
        "genuineness": 4.444586753845215,
        "identity": 0.254038542509079,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c777be39346e81687f038967916155c54c47f843333386ac9188e30463dc90d6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "c7d4b6be7f89fb02837437b8994e4f87cb519be618d10fde8d1dcda2962ad85e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0d2e865630db8ba13ca75d35d93d093aedb5348dcb827564c013715e3796f7e6",
      "generation_seconds_batch": 24.69119016698096,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.819552421569824,
        "target_z": 0.42382808685156165,
        "ce": 6.157639026641846,
        "genuineness": 4.18099308013916,
        "identity": 0.5403944253921509,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c7d4b6be7f89fb02837437b8994e4f87cb519be618d10fde8d1dcda2962ad85e.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "6eefedbdeeb8c71f28474998984f804f0a28dfe446349c62c61f17bb00d93b6f",
      "generation_seconds_batch": 19.066596223972738,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.231760025024414,
        "target_z": -0.02832030023160551,
        "ce": 6.3641486167907715,
        "genuineness": 4.344170093536377,
        "identity": 0.5841755867004395,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "c83aa152c1e7ac5f6eeb07bd37894161c05c2a639e42cd871210cebd56e515c6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "3df04285f497473927697e3e5013978a42d9cdbd5be825be6630819bd5457809",
      "generation_seconds_batch": 18.817335570929572,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6295127868652344,
        "target_z": 1.046875058745013,
        "ce": 5.831989288330078,
        "genuineness": 3.760498285293579,
        "identity": -0.07367638498544693,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c83aa152c1e7ac5f6eeb07bd37894161c05c2a639e42cd871210cebd56e515c6.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "c87b223895fc67a86195587e840857422d74def8e12e608765427e5eaf85d821",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "feff8a56b2f61900756a1c173c5c1955629f588b865507802f5d5222e0e7bb4c",
      "generation_seconds_batch": 15.690243636025116,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7734596729278564,
        "target_z": -0.38085933649336035,
        "ce": 6.523001670837402,
        "genuineness": 4.231201171875,
        "identity": 0.5142805576324463,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c87b223895fc67a86195587e840857422d74def8e12e608765427e5eaf85d821.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "13c8668b281d6241359f41abdffee8b6eb9ddc84eb566d86e15a460b12da440b",
      "generation_seconds_batch": 18.039080351009034,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7683814764022827,
        "target_z": -0.3847656448801721,
        "ce": 6.308549880981445,
        "genuineness": 4.300237655639648,
        "identity": 0.417952299118042,
        "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "c8e5735222609312935ab55f2a833a45753b43968feb30cd62e5c461bc7e554d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8616bed550e6f2d9a9d0e1f4f7b5a9cd9eee0773af9a9e39cbc506d9f68169d8",
      "generation_seconds_batch": 23.774076825007796,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4873251914978027,
        "target_z": 0.9374998911068051,
        "ce": 6.070269584655762,
        "genuineness": 4.111956596374512,
        "identity": 0.5313030481338501,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c8e5735222609312935ab55f2a833a45753b43968feb30cd62e5c461bc7e554d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "c90c399df97ebd1505cf92157b6cb469d98154f47e9e0bb30e4107e4c3db21f7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "f10a384f7e52df3cad9ffd630f3cea57ba87242bace8c7cb7cb84d6d2b10154a",
      "generation_seconds_batch": 24.31267366395332,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.258810043334961,
        "target_z": 0.7617188563857858,
        "ce": 6.252951145172119,
        "genuineness": 4.118232727050781,
        "identity": 0.6577717065811157,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/c90c399df97ebd1505cf92157b6cb469d98154f47e9e0bb30e4107e4c3db21f7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "cbbb3bd97ddf0bf2bc97a3516c3ef426e08800e2e21abfb827e871d5065e404f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f0c6ea0b96440bf8638d0ca8e8e7c134f29be41258e1b5cca895da48c44c3561",
      "generation_seconds_batch": 24.430934706004336,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4755098819732666,
        "target_z": 0.15917975134938156,
        "ce": 6.348263263702393,
        "genuineness": 3.9801597595214844,
        "identity": 0.5463994741439819,
        "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.125,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cbbb3bd97ddf0bf2bc97a3516c3ef426e08800e2e21abfb827e871d5065e404f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "cc1bcf233c318be942e26d98d9f5cf2c2443035e42d7bf5310e47474c807ff10",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "7a8b3636630ff1f35b1a0b856655e2b6ab2a40101ce090a080930c52da728cbc",
      "generation_seconds_batch": 25.54227895499207,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.269355773925781,
        "target_z": 1.5390623961216232,
        "ce": 5.657250881195068,
        "genuineness": 3.5471129417419434,
        "identity": 0.20961929857730865,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cc1bcf233c318be942e26d98d9f5cf2c2443035e42d7bf5310e47474c807ff10.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "ccb5b46de136a02d3b0f692cdf1ce82f8200fc1337beda82c67063d6a19a61b2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a6998332cfc6bdca85ccb14f1957272828858a0e3977efda96f9c401c112c0d7",
      "generation_seconds_batch": 24.191576206008904,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.268836498260498,
        "genuineness": 4.243753433227539,
        "identity": 0.5248506665229797,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ccb5b46de136a02d3b0f692cdf1ce82f8200fc1337beda82c67063d6a19a61b2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "cd1392cdaea49602bbe508ee52778a8dd8a7d0f660c61db27af5ccc269998403",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b25610a0f62ef45f4e83bf92b6e6dad37bddf4e854576125055ffd422f7a3fd0",
      "generation_seconds_batch": 25.042329836986028,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9138875007629395,
        "target_z": 1.2656250272232987,
        "ce": 6.229123115539551,
        "genuineness": 3.998987913131714,
        "identity": 0.5254780650138855,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cd1392cdaea49602bbe508ee52778a8dd8a7d0f660c61db27af5ccc269998403.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "cd2945c4bd92630fa5c869584b22e65be4111ae9e93de2cc7d67ccdebba3920d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "efbf7e8222aa31e7de4a89652063bd75cdcfc5d07af7de425da9623c45c8bbd4",
      "generation_seconds_batch": 16.548658450017683,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0201382637023926,
        "target_z": 0.5781250214920779,
        "ce": 6.205295085906982,
        "genuineness": 4.268857479095459,
        "identity": 0.5751485824584961,
        "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cd2945c4bd92630fa5c869584b22e65be4111ae9e93de2cc7d67ccdebba3920d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "ce4dc21823fc63e5c0e863a64ddc29f33c0e8b7d8bdb52cea7d4aca6ed5ef29b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "d002ed0cc50fd79e6c3c3df2ad11c6576a9b7f313b73a4bc5b236db652f0f14b",
      "generation_seconds_batch": 17.519817364984192,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.060763120651245,
        "target_z": 0.6093749383893766,
        "ce": 5.8875885009765625,
        "genuineness": 3.722842216491699,
        "identity": 0.4300270676612854,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás liberado.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ce4dc21823fc63e5c0e863a64ddc29f33c0e8b7d8bdb52cea7d4aca6ed5ef29b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "cea2173038dba4b295af6852699707bbcd2634bb24a566916c225dc51df6c671",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "584f8ec94c7158d1144130a264892ce99368448b39aebcaf98ab102ea9ea1383",
      "generation_seconds_batch": 24.868275535991415,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7818562984466553,
        "target_z": 1.1640624763587142,
        "ce": 5.95112943649292,
        "genuineness": 4.093128204345703,
        "identity": 0.11077268421649933,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cea2173038dba4b295af6852699707bbcd2634bb24a566916c225dc51df6c671.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "cedf536601d9eaed538fa8654f4991059ed69fc461a40331331a99614ba30b68",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ccd22b9021b3f9c6fe4abed282b5ffb4ad09c4e231bd26b3e330b0eaace8e0b3",
      "generation_seconds_batch": 18.694358405075036,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.157637119293213,
        "target_z": 1.4531248954052207,
        "ce": 6.022613525390625,
        "genuineness": 3.735394239425659,
        "identity": 0.4812396466732025,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cedf536601d9eaed538fa8654f4991059ed69fc461a40331331a99614ba30b68.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5641f877b793f2b27f459ca7044faf270884c083d2c37a7eadf3b2277de37641",
      "generation_seconds_batch": 18.10996663500555,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7759987115859985,
        "target_z": -0.37890622814972075,
        "ce": 6.356205940246582,
        "genuineness": 4.494794845581055,
        "identity": 0.5913233757019043,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "cf8fbda87fa6a25cef881f30f538ee31bd41d46e30b6841261ae68516c5a2e7f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "2ecd0b39a63451e4d83a5667dd3ee87425e918f5681ef6c253d02ec8a0972b71",
      "generation_seconds_batch": 31.567206152016297,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.974824905395508,
        "target_z": 1.3124999942687792,
        "ce": 6.117925643920898,
        "genuineness": 3.9048471450805664,
        "identity": 0.5230717658996582,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cf8fbda87fa6a25cef881f30f538ee31bd41d46e30b6841261ae68516c5a2e7f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "cff416421c858f410ede3871768fe09da69fcc9b7cf593c77662748136448ca7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "c9c00e6d043a9f170c795c02e9faa503d8309be9114cd5d730296721003f548a",
      "generation_seconds_batch": 24.803521528025158,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.370918273925781,
        "target_z": 1.6171874634634675,
        "ce": 5.9431867599487305,
        "genuineness": 3.873466968536377,
        "identity": 0.3672122657299042,
        "hypothesis": "En que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que nos ha visto.",
        "wer": 0.29411764705882354,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/cff416421c858f410ede3871768fe09da69fcc9b7cf593c77662748136448ca7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "d02b6114b38e07a34c2d2acb22ba94adc6915ff879e79ffbbe76b0fb51aea70a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "de3b1421d7f7db8c048af79c8855c508c184857a97e61a70dd912524e59b68c2",
      "generation_seconds_batch": 21.34410384099465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 5.700935363769531,
        "genuineness": 4.15588903427124,
        "identity": 0.5653970241546631,
        "hypothesis": "I've tried the petite boat. It is pretty fenêtre. We've regarded what.",
        "wer": 0.8947368421052632,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d02b6114b38e07a34c2d2acb22ba94adc6915ff879e79ffbbe76b0fb51aea70a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "d048e5b0a27ffc2251483d39a32229f94fd05b8ea452967d9db5feefdd50beb6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c0f20cb184a0bdbfffce4d0fa620ae8fb91ba9c566444d090e414a0a5bc04241",
      "generation_seconds_batch": 25.93738785700407,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.618966579437256,
        "target_z": 0.2695311522110454,
        "ce": 6.324435234069824,
        "genuineness": 4.118232727050781,
        "identity": 0.3855307400226593,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d048e5b0a27ffc2251483d39a32229f94fd05b8ea452967d9db5feefdd50beb6.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "d0aefac8b696fa5f788ded150dc339b07f36c1c318686c59f7386fbb42c276a7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7a865ef2fc5f3aa5fa584247ca12ecb301876ceb783d18db821e42453c201a21",
      "generation_seconds_batch": 17.717805989086628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.606271505355835,
        "target_z": 0.25976570219237993,
        "ce": 6.133810997009277,
        "genuineness": 4.337893962860107,
        "identity": 0.6740851402282715,
        "hypothesis": "Des clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.",
        "wer": 0.041666666666666664,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d0aefac8b696fa5f788ded150dc339b07f36c1c318686c59f7386fbb42c276a7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "d0bd7c22482cc8b0925d6f6e32d167ee14e6e0ea8016d1031b10027e65f1dc2d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "994d3b4b224ba1fae54ea980a4a865cd7d8d746d3f2d99ec1fac27599afa866e",
      "generation_seconds_batch": 25.190847465069965,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.073068618774414,
        "target_z": -0.15039071795323708,
        "ce": 6.459460258483887,
        "genuineness": 4.13078498840332,
        "identity": 0.2905730605125427,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d0bd7c22482cc8b0925d6f6e32d167ee14e6e0ea8016d1031b10027e65f1dc2d.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "d1192c60026f6c7a00e4ad32ee0f1ce2973dc64604954dec48b1455444b2f2cc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cbc17b12a2602ead5ec519e1e2d6b7ac3105715f4fa4eee32b892444f4edb87b",
      "generation_seconds_batch": 25.005971884937026,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7230682373046875,
        "target_z": 0.34960941959606173,
        "ce": 6.197352409362793,
        "genuineness": 4.293961524963379,
        "identity": 0.627626895904541,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d1192c60026f6c7a00e4ad32ee0f1ce2973dc64604954dec48b1455444b2f2cc.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I wrote the number on the envelope.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4b5c824b1678597bab7fa14de07808aff8cf5a99181e6db566ef48c0d3e3a784",
      "generation_seconds_batch": 18.27715502900537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6592018604278564,
        "target_z": -0.46875003725293507,
        "ce": 6.41180419921875,
        "genuineness": 3.886019229888916,
        "identity": 0.33583948016166687,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "d122443572c9a42c484b7a8cc3b62cc2fd7edd7a3b06ea14a0d4d48611244e3f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "c0393fd1c4d809056b20c0e547291f1c5a19fcaab5dde195243be19618e68dbd",
      "generation_seconds_batch": 25.09561674494762,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.385762929916382,
        "target_z": 0.8593750071640259,
        "ce": 6.340320587158203,
        "genuineness": 4.250029563903809,
        "identity": 0.5030891299247742,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de nuevo.",
        "wer": 0.11764705882352941,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d122443572c9a42c484b7a8cc3b62cc2fd7edd7a3b06ea14a0d4d48611244e3f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "d148c0f3d95d0334e6d5a640430e3c11b778e4174cb0f425dcaee3644d04710d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3d39ac60b79d9c5233b2daf8802d4fc6da7c6ab4218b711611b98895d9001700",
      "generation_seconds_batch": 23.97754695697222,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.035762310028076,
        "target_z": 1.3593749613142596,
        "ce": 6.38003396987915,
        "genuineness": 4.174716949462891,
        "identity": 0.6508963108062744,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay de aquí.",
        "wer": 0.11764705882352941,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d148c0f3d95d0334e6d5a640430e3c11b778e4174cb0f425dcaee3644d04710d.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "d153052c4f2db658aa9789c81f5bb47d019a6263e29e3a76f837446489c726ad",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "085daaca1ec5c9d2221978e2c0cc76538ae4330f888ff6cc5205c72500004e7d",
      "generation_seconds_batch": 21.380664186086506,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3612520694732666,
        "target_z": 0.07128905058980681,
        "ce": 6.41180419921875,
        "genuineness": 4.331617832183838,
        "identity": 0.3988383114337921,
        "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d153052c4f2db658aa9789c81f5bb47d019a6263e29e3a76f837446489c726ad.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "d199fa422693444e7871263e08dea856dbdfc32e56e986ff2f74ca4cb3f555ec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a536e7ee579c40a8e481bf95b8cb788cb21be7369e2866eee0d4563df0309c3d",
      "generation_seconds_batch": 25.36313484807033,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9947476387023926,
        "target_z": 0.5585937546566169,
        "ce": 6.197352409362793,
        "genuineness": 4.024092197418213,
        "identity": 0.3360138237476349,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d199fa422693444e7871263e08dea856dbdfc32e56e986ff2f74ca4cb3f555ec.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "d1b8c69320c021fa2e5626ea1b3951d3e59c25b62153392749d9c650d1fbba04",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "5c6d298bb0216efb94a2290126417f7c98a7f6f3a5884174b0448fabc67de95e",
      "generation_seconds_batch": 22.85638883896172,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0662312507629395,
        "target_z": 1.382812628236065,
        "ce": 6.213237762451172,
        "genuineness": 3.9299514293670654,
        "identity": 0.5164771676063538,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d1b8c69320c021fa2e5626ea1b3951d3e59c25b62153392749d9c650d1fbba04.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dae69599303dd6f879948985d3305e5071223ecf35236ed6c791a5757aa6d7af",
      "generation_seconds_batch": 18.63862544600852,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0959203243255615,
        "target_z": -0.1328124677618831,
        "ce": 6.300607204437256,
        "genuineness": 4.482243061065674,
        "identity": 0.6695410013198853,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "d25f63831bbe907981e27e47994215809dcae9fcba02c6b7d98ffc0e84769b87",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "4df5bb8841fed9f1b223aaf63fa6b97b4d92457ea7a6418c077daedc88405ec9",
      "generation_seconds_batch": 18.69971864297986,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.499630928039551,
        "target_z": 0.17773441816325652,
        "ce": 6.1020402908325195,
        "genuineness": 4.532451152801514,
        "identity": 0.5528377294540405,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam, neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d25f63831bbe907981e27e47994215809dcae9fcba02c6b7d98ffc0e84769b87.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "d25f73ffea8282963dbd06cab8eb7ec247d00b8b1f8419cf39d1f018a32b469b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "54b33e938a62502331d9c950bfa1e904450a253dc8cbc54556892c316b1bffd2",
      "generation_seconds_batch": 23.608127934043296,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6295127868652344,
        "target_z": 1.046875058745013,
        "ce": 6.24500846862793,
        "genuineness": 4.005263805389404,
        "identity": 0.23200684785842896,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d25f73ffea8282963dbd06cab8eb7ec247d00b8b1f8419cf39d1f018a32b469b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "d273b965721b4f679dbe1f4f8ff8d9d7833fcb3a65de2c5f13472d6fc8a63afb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6f23e2feabe76e77fd06055b13766ec8b3ef91c744a5a263a9d62a2974396d27",
      "generation_seconds_batch": 22.34501046105288,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.131856918334961,
        "target_z": 0.6640625222084805,
        "ce": 6.38003396987915,
        "genuineness": 4.068024158477783,
        "identity": 0.5998440384864807,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d273b965721b4f679dbe1f4f8ff8d9d7833fcb3a65de2c5f13472d6fc8a63afb.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "d2f32e643dc3d1695f18f0c98fad79e09bdb0db2c092cae801be94485f9e77ed",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e536161359da99db15c73f3b8e1df54a7f5560fde69d54e0d7acb042517129e9",
      "generation_seconds_batch": 17.717805989086628,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1420130729675293,
        "target_z": 0.6718749555830389,
        "ce": 6.157639026641846,
        "genuineness": 4.394378662109375,
        "identity": 0.7287397384643555,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d2f32e643dc3d1695f18f0c98fad79e09bdb0db2c092cae801be94485f9e77ed.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "d317a35725d403928dd65437392d7752911adad379f5d0c43e3927407d0c8834",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4962c9265803b2350e911fc5c6325d9f449002a5416c063777d93005260b4ea2",
      "generation_seconds_batch": 17.804942399961874,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5584189891815186,
        "target_z": 0.9921874749259091,
        "ce": 6.292664527893066,
        "genuineness": 4.168440818786621,
        "identity": 0.5056900978088379,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d317a35725d403928dd65437392d7752911adad379f5d0c43e3927407d0c8834.mp3"
    },
    {
      "id": "heldout-de-4",
      "language": "de",
      "sentences": [
        "Ich schrieb die Nummer auf den Umschlag.",
        "Lies sie genau... und prüfe die letzten beiden Ziffern.",
        "Ruf an, wenn du Zeit hast."
      ],
      "text": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau... und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-4",
      "key": "d35e8b8c16875f2ec3d00b7efd687bdd23b9a0b825736ba1b38c260a59166dfb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5eef08ef3e9c174d6bb17494a5fc13e23cf25ccd28e53751c5e1543b633fd81e",
      "generation_seconds_batch": 17.559631027979776,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.5271707773208618,
        "target_z": -0.570312496417987,
        "ce": 6.1894097328186035,
        "genuineness": 4.168440818786621,
        "identity": 0.6327505111694336,
        "hypothesis": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d35e8b8c16875f2ec3d00b7efd687bdd23b9a0b825736ba1b38c260a59166dfb.mp3"
    },
    {
      "id": "heldout-nl-0",
      "language": "nl",
      "sentences": [
        "Je bericht kwam nadat ik vertrokken was.",
        "Ik las het twee keer... en legde mijn telefoon weg.",
        "Zeg maar wanneer we kunnen praten."
      ],
      "text": "Je bericht kwam nadat ik vertrokken was. Ik las het twee keer... en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-0",
      "key": "d3bcf6377698141c0f6f4b222daf4e97c3a7e475e2150c01ec4d499b4cd4225c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "13b217b4c13f87795fdf1c638303b4125b0e59f02aed676c0f24181a9a3d1c89",
      "generation_seconds_batch": 20.921538257040083,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.136934995651245,
        "target_z": 0.6679687388957597,
        "ce": 6.2767791748046875,
        "genuineness": 4.20609712600708,
        "identity": 0.6518741846084595,
        "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las ze twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.",
        "wer": 0.043478260869565216,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d3bcf6377698141c0f6f4b222daf4e97c3a7e475e2150c01ec4d499b4cd4225c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "d3bfccf9b718810ce263f00c3dfdd4aa239616cba22f66e9bc6dee6156af2424",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d9ccf017d38451706f7b474673de2e03fde0f24f4cb10b4db0e9333a4226e9bb",
      "generation_seconds_batch": 23.621111784945242,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.954512596130371,
        "target_z": 1.2968751275196624,
        "ce": 6.300607204437256,
        "genuineness": 4.256305694580078,
        "identity": 0.6037881374359131,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contient.",
        "wer": 0.2631578947368421,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d3bfccf9b718810ce263f00c3dfdd4aa239616cba22f66e9bc6dee6156af2424.mp3"
    },
    {
      "id": "heldout-fr-4",
      "language": "fr",
      "sentences": [
        "J’ai écrit le numéro sur l’enveloppe.",
        "Lis-le bien... et vérifie les deux derniers chiffres.",
        "Appelle-moi quand tu auras un moment."
      ],
      "text": "J’ai écrit le numéro sur l’enveloppe. Lis-le bien... et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-4",
      "key": "d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f25277b36e8a8c65cee72cf75bf1a9cacf42a270640ab3804145a242b2e0eff3",
      "generation_seconds_batch": 18.18009824794717,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4967020750045776,
        "target_z": -0.5937499799407272,
        "ce": 6.1020402908325195,
        "genuineness": 4.457139015197754,
        "identity": 0.7247376441955566,
        "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "d40caca87f47d606bc0ccf77eabb7fbc6eaf08e8f68b4bb694b4dd7c7c409393",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a68d1b7ee85b4b0daae471aaea0042c5cc9af73bbb3308a9f13673e5ae51a9af",
      "generation_seconds_batch": 24.34332014201209,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.131856918334961,
        "target_z": 0.6640625222084805,
        "ce": 6.1894097328186035,
        "genuineness": 3.8295347690582275,
        "identity": 0.23407843708992004,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d40caca87f47d606bc0ccf77eabb7fbc6eaf08e8f68b4bb694b4dd7c7c409393.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "d426d173f7ef9d5b8f10a810ef13742b1f9ea3861183710af6db9c3dfaa9be35",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8fe49b0ecef2fc589bea179a05daae1f8cba5c9e0c66127a343fe2328685a8ec",
      "generation_seconds_batch": 23.05446971289348,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5021698474884033,
        "target_z": 0.17968743480736357,
        "ce": 6.1894097328186035,
        "genuineness": 4.256305694580078,
        "identity": 0.5259329676628113,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d426d173f7ef9d5b8f10a810ef13742b1f9ea3861183710af6db9c3dfaa9be35.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "d4c98e9dafdfbbff7c1bc05689c7ea25b0659d4cf3dfc41b5fdf818cc322eabc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4d7372b071b943983b9b1755131210fd7b53a4c965c41eec5754fbe704de3f3e",
      "generation_seconds_batch": 18.31112974905409,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.416231632232666,
        "target_z": 0.8828124906867663,
        "ce": 5.700935363769531,
        "genuineness": 3.8546390533447266,
        "identity": 0.5570180416107178,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d4c98e9dafdfbbff7c1bc05689c7ea25b0659d4cf3dfc41b5fdf818cc322eabc.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "d4cb94e221381b747ee8fe0cc98d2fd663d497c1ec89035c5dfd5ea8e5b53acd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9b8cc8ef2d3193af312c3925cc6edcc2185f7d74c7d5850738f0a0468e3eac03",
      "generation_seconds_batch": 16.45801823900547,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8424038887023926,
        "target_z": 0.44140615364385055,
        "ce": 6.395919322967529,
        "genuineness": 3.9550557136535645,
        "identity": 0.380405455827713,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d4cb94e221381b747ee8fe0cc98d2fd663d497c1ec89035c5dfd5ea8e5b53acd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "d4f66eca05ac307437182e27f0d2c8294e6c9640cba56f85b64ca7a2b868ad07",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "277c89e6ec71dcbf2fafce4fa057d8e72ade5c8cf53450b91b0304c0867c3f9e",
      "generation_seconds_batch": 24.667846460011788,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.167793273925781,
        "target_z": 1.460937328779779,
        "ce": 5.935244083404541,
        "genuineness": 4.20609712600708,
        "identity": 0.5469788312911987,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d4f66eca05ac307437182e27f0d2c8294e6c9640cba56f85b64ca7a2b868ad07.mp3"
    },
    {
      "id": "heldout-nl-4",
      "language": "nl",
      "sentences": [
        "Ik schreef het nummer op de envelop.",
        "Lees het goed... en controleer de laatste twee cijfers.",
        "Bel me wanneer je even tijd hebt."
      ],
      "text": "Ik schreef het nummer op de envelop. Lees het goed... en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-4",
      "key": "d53027f869511c127e1dbaf993d24e5eae882d95b35cdcba346060f9e8c45504",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "283bea7fbf591c5cd1af74e6acd3959ae5d7114e0d419d8fff53c0f44d2fedc1",
      "generation_seconds_batch": 16.626545223989524,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.682443141937256,
        "target_z": 0.318359319299698,
        "ce": 6.213237762451172,
        "genuineness": 4.375550270080566,
        "identity": 0.6105221509933472,
        "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d53027f869511c127e1dbaf993d24e5eae882d95b35cdcba346060f9e8c45504.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "d5596602a0c79c55b6ed4f98af1b5d87a85c5f3d0e95bda8d82dc40bab59e0b6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b8fa0202a73e4f12a2c4b3ab1f04777db8775f29b8868adfdcea701025fb9124",
      "generation_seconds_batch": 24.613500033970922,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5212128162384033,
        "target_z": 0.19433588493395937,
        "ce": 6.4912309646606445,
        "genuineness": 4.306513786315918,
        "identity": 0.6380081176757812,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d5596602a0c79c55b6ed4f98af1b5d87a85c5f3d0e95bda8d82dc40bab59e0b6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "d57a413bf51c647d456ba512393abf6f96e4477dbd71f72464cb89e7e515adae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "8b8e7ce837d9ca13a1d0c6404b990260ba6cc3265a3ef8577baf8f14f73eab8d",
      "generation_seconds_batch": 24.723739272914827,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.233419418334961,
        "target_z": 0.7421875895503247,
        "ce": 5.808161735534668,
        "genuineness": 3.415316104888916,
        "identity": 0.25724297761917114,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abriendo.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d57a413bf51c647d456ba512393abf6f96e4477dbd71f72464cb89e7e515adae.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "d62783f92d1db9863c78b52c56124b78c7c33d4d81b5459820b401d328055fe4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "03d30147549fa5f5aa4d786ca8b43c9acac407a8172a9e81d16a066aaae74fb0",
      "generation_seconds_batch": 22.431398672051728,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.954512596130371,
        "target_z": 1.2968751275196624,
        "ce": 6.24500846862793,
        "genuineness": 4.074300289154053,
        "identity": 0.4897128641605377,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d62783f92d1db9863c78b52c56124b78c7c33d4d81b5459820b401d328055fe4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "d66d49de82e9433f2097347a752148630a9302d47f4d46dc250ac80252b38230",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "a69274b1ebbfdb1b3cee03f29ae9b2687ac47eae14cf358d756d70861100c2e3",
      "generation_seconds_batch": 24.502041860017926,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.685761451721191,
        "target_z": 1.8593747320654284,
        "ce": 6.24500846862793,
        "genuineness": 4.532451152801514,
        "identity": 0.6138414144515991,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d66d49de82e9433f2097347a752148630a9302d47f4d46dc250ac80252b38230.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "d79095ea0552f76ceba9b148486a286833d85320e7b20d682e8bedee62ee0bfe",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "06602f0790d4e3f8ff56a463016d9554772235ea2dd0697beac0a2ec1c8a1df3",
      "generation_seconds_batch": 24.406232776935212,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.046441555023193,
        "genuineness": 3.8169827461242676,
        "identity": 0.2993227243423462,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d79095ea0552f76ceba9b148486a286833d85320e7b20d682e8bedee62ee0bfe.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "d8345171e57f4bb0bc200d42aa4d02f657044bb8aaea51309b36e01f52c39972",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "31f324d8715363aedbe2b0d5d96a21b3020b992cfda236e764c5fb2a6c169f87",
      "generation_seconds_batch": 26.72081136808265,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.933810234069824,
        "target_z": 0.5117187876111364,
        "ce": 6.403861999511719,
        "genuineness": 4.017816066741943,
        "identity": 0.42002785205841064,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d8345171e57f4bb0bc200d42aa4d02f657044bb8aaea51309b36e01f52c39972.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "d86b2690d6ab4300ad6e53007acd41a6299253aac922ca1a5020e8c4f3bfe35c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9aeeb4557579744a2fabbf5410514c6a57010bc7452cb2c3c7adf0259b551c9a",
      "generation_seconds_batch": 24.618533052969724,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.035762310028076,
        "target_z": 1.3593749613142596,
        "ce": 5.8875885009765625,
        "genuineness": 3.6977379322052,
        "identity": 0.36705732345581055,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d86b2690d6ab4300ad6e53007acd41a6299253aac922ca1a5020e8c4f3bfe35c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "d89a52db99a20ddb42d71ac267c5b09d4526194ec70d6b6ce98b5e8c0397375c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1844a0d2f823587c570f7432bbf88334072ba12b92671c79e66c93051a184cc9",
      "generation_seconds_batch": 21.99821150198113,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4831268787384033,
        "target_z": 0.1650389846807678,
        "ce": 6.070269584655762,
        "genuineness": 4.017816066741943,
        "identity": 0.6633812189102173,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d89a52db99a20ddb42d71ac267c5b09d4526194ec70d6b6ce98b5e8c0397375c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "d8e5a8868f3692bf855e4a25e5359fbb316678be6f803690b92c10fe4a298cc0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b8f00a67c85ec010bcfc592e3007e3a04be1532cd9ad65bb7264f6c4d35f1c5b",
      "generation_seconds_batch": 25.039864843012765,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.852950096130371,
        "target_z": 1.2187500601778183,
        "ce": 5.645336627960205,
        "genuineness": 4.3881025314331055,
        "identity": 0.5409914255142212,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vie fenêtre. We've regarded ensemble what.",
        "wer": 0.3684210526315789,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d8e5a8868f3692bf855e4a25e5359fbb316678be6f803690b92c10fe4a298cc0.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "d9bf6fb8c89fd5b124383cdc6043b6fcb81f91e0df09dbe64a86e8e88d68579e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b61952f0a4c14feb669019e31eb9d77f831c08f95241cf3ff6b615a3d43dacaf",
      "generation_seconds_batch": 21.415874387021177,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8935749530792236,
        "target_z": 1.249999977075117,
        "ce": 6.09409761428833,
        "genuineness": 4.137060642242432,
        "identity": 0.6192243695259094,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d9bf6fb8c89fd5b124383cdc6043b6fcb81f91e0df09dbe64a86e8e88d68579e.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "d9d39074292e1fcccb7b7f5db91e620ececbaaf300b2422e72b1911121d4413d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "882c3a78efdbaeeed3b5e0e9de889b321b5d4a7b9916591ea10137ae2aaeed91",
      "generation_seconds_batch": 16.79419483698439,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3485567569732666,
        "target_z": 0.06152341717207628,
        "ce": 6.348263263702393,
        "genuineness": 4.105680465698242,
        "identity": 0.7228997945785522,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/d9d39074292e1fcccb7b7f5db91e620ececbaaf300b2422e72b1911121d4413d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "da0eaa64b92672e5c2cfb0d3cd74fa80594bd15389c59f64c9d960f11dbfce2a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dd8feb6844a1a22a9a0cad6f242e4cfea7e720748e0f3c69adff6149a6d794b4",
      "generation_seconds_batch": 24.904970320058055,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9185757637023926,
        "target_z": 0.49999995415023374,
        "ce": 6.205295085906982,
        "genuineness": 4.030367851257324,
        "identity": 0.4712934195995331,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/da0eaa64b92672e5c2cfb0d3cd74fa80594bd15389c59f64c9d960f11dbfce2a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "da34bad02270f5144da67beaed1e793340770623e9074ff4981f961e7cb33c45",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eb4b590f22c7a3514a4f419d701885938ee0a71d7ca5c3a1882ce445d7f357cd",
      "generation_seconds_batch": 22.94981826399453,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.137324810028076,
        "target_z": 1.437500028656104,
        "ce": 6.23706579208374,
        "genuineness": 4.362998008728027,
        "identity": 0.6020258665084839,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/da34bad02270f5144da67beaed1e793340770623e9074ff4981f961e7cb33c45.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "da852da9a2e22ccafdad276e0801b1d584717db85728a448cb62ef327ddee139",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "c81f07d7b4544ce93aa7dc2b42bfee60406da8fb81a79a04634d67b2d03e0525",
      "generation_seconds_batch": 19.19931539101526,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7310752868652344,
        "target_z": 1.1250001260868572,
        "ce": 5.649308204650879,
        "genuineness": 3.490628719329834,
        "identity": 0.41030043363571167,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás abierto.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/da852da9a2e22ccafdad276e0801b1d584717db85728a448cb62ef327ddee139.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Your message arrived after I had left.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "18fc91c0a47e2c774111d2ec0befcc3197d4087245157891b3d68c5196852f1f",
      "generation_seconds_batch": 18.406741626095027,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.7451401948928833,
        "target_z": -1.1718750014328052,
        "ce": 6.316492557525635,
        "genuineness": 3.986435890197754,
        "identity": 0.381661593914032,
        "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "db2507b507c94614068d9436b5708b8abcc0ac4cc09e9c8b595a691f18dc64ce",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "eb906bdc3094b40d360ddd7cd8c00324eebd6c3d0b40be6bf9eea7c20167852c",
      "generation_seconds_batch": 24.884573912015185,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9138875007629395,
        "target_z": 1.2656250272232987,
        "ce": 6.205295085906982,
        "genuineness": 3.9676074981689453,
        "identity": 0.6215794086456299,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/db2507b507c94614068d9436b5708b8abcc0ac4cc09e9c8b595a691f18dc64ce.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "db629c6cfc50b71fe39fd697363659d1403998478f48d3d61b182e54b4bd6dcd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "de083f275dcfb207b335c38d53f23041962764d5e2544b642cdad03b18320e22",
      "generation_seconds_batch": 16.36079486995004,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3815646171569824,
        "target_z": 0.08691410073798866,
        "ce": 6.308549880981445,
        "genuineness": 3.8295347690582275,
        "identity": 0.40134692192077637,
        "hypothesis": "Your message arrived after I had left. I read it twice. Before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/db629c6cfc50b71fe39fd697363659d1403998478f48d3d61b182e54b4bd6dcd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "db63b5d53d4abf5124e5ba4965346054f5fa30fe04eadb042f4175eb223a31c6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "04386ce2d5c2fcd1a0361265789aa58a0b1c7337d55e54d02107ca9b198bae43",
      "generation_seconds_batch": 24.410452560056,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5888876914978027,
        "target_z": 1.0156249584486494,
        "ce": 6.268836498260498,
        "genuineness": 3.8169827461242676,
        "identity": 0.22163234651088715,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/db63b5d53d4abf5124e5ba4965346054f5fa30fe04eadb042f4175eb223a31c6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "db72cc713e57473573c11db07b19b87b2cf81a76a34cec5f128832cb0db6027c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ee0b80ec004ecd1900b300750e8f6a46632b95657b43c3684f701d8a0accd67c",
      "generation_seconds_batch": 23.728623947012238,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5076379776000977,
        "target_z": 0.9531251246540521,
        "ce": 6.1894097328186035,
        "genuineness": 4.137060642242432,
        "identity": 0.415749192237854,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/db72cc713e57473573c11db07b19b87b2cf81a76a34cec5f128832cb0db6027c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "dc21206a67ee3c978f6f6730a892ee1167546510b74f8006e865edf01c456c2d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2390bc7d37a6efa82fc6d9f4d550a76a79ae36b9aac674151b63de0525530cc4",
      "generation_seconds_batch": 18.490725807962008,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 6.221180438995361,
        "genuineness": 4.369274139404297,
        "identity": 0.5487062931060791,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/dc21206a67ee3c978f6f6730a892ee1167546510b74f8006e865edf01c456c2d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "dc352d15c527abaa1f027f5d685b9acdc1f68662c246eb902681dbd3d795c20b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "877d3e62ce7b19797f77fd88bdaa829e456f3c1ff84e92bb89b7efe9c1237624",
      "generation_seconds_batch": 24.058952579973266,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6291229724884033,
        "target_z": 0.27734376898466884,
        "ce": 6.403861999511719,
        "genuineness": 4.13078498840332,
        "identity": 0.5705944299697876,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/dc352d15c527abaa1f027f5d685b9acdc1f68662c246eb902681dbd3d795c20b.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "dc539679ff4a5119780bc54de2529fd54522d1f173c9b6d57599996940f2b878",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "dc65b5d7d8ce342b7ecde7683ce977319bf7db956024c728c7880e38e5d239c9",
      "generation_seconds_batch": 16.45801823900547,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4215548038482666,
        "target_z": 0.11767580932402681,
        "ce": 6.260893821716309,
        "genuineness": 3.7416701316833496,
        "identity": 0.3996264934539795,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/dc539679ff4a5119780bc54de2529fd54522d1f173c9b6d57599996940f2b878.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "dcf810994ec08399b258ae2445e40e1b45f4906eb148a4cc89b9367520474bce",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "d2b27f7c9f8451aa883e268ce57fb807bf3797730a2d9a91c038ef2551c101ff",
      "generation_seconds_batch": 23.45693346695043,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2029504776000977,
        "target_z": 0.7187499226285194,
        "ce": 6.078212261199951,
        "genuineness": 4.256305694580078,
        "identity": 0.45549315214157104,
        "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/dcf810994ec08399b258ae2445e40e1b45f4906eb148a4cc89b9367520474bce.mp3"
    },
    {
      "id": "heldout-en-4",
      "language": "en",
      "sentences": [
        "I wrote the number on the envelope.",
        "Read it carefully... and check the last two digits.",
        "Call me when you have a moment."
      ],
      "text": "I wrote the number on the envelope. Read it carefully... and check the last two digits. Call me when you have a moment.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-4",
      "key": "de23e2c9d5b6ed3efdd6a2e0927ebca32dd4d9153c1e54e2c050f73ca0205fad",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I wrote the number on the envelope.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Call me when you have a moment.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "03a0771569e5fbc5b6a7b7240fd07047c01e3dad1e687240c18dd97a1f77000d",
      "generation_seconds_batch": 24.479064603918232,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.034982919692993,
        "target_z": -0.17968743480736357,
        "ce": 6.38797664642334,
        "genuineness": 3.873466968536377,
        "identity": 0.5824692249298096,
        "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/de23e2c9d5b6ed3efdd6a2e0927ebca32dd4d9153c1e54e2c050f73ca0205fad.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "de2999f3c99b4cab8d8f153d851d2fa8b6ae737de814d098ba14cb07ad52a5c5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "db09a854397804f528422d114ddabe0c5db7c728aa1aba2276a73c9565c352a7",
      "generation_seconds_batch": 17.219861789955758,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.594355583190918,
        "target_z": 1.7890624648962727,
        "ce": 6.24500846862793,
        "genuineness": 4.293961524963379,
        "identity": 0.5996189117431641,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/de2999f3c99b4cab8d8f153d851d2fa8b6ae737de814d098ba14cb07ad52a5c5.mp3"
    },
    {
      "id": "heldout-es-2",
      "language": "es",
      "sentences": [
        "La carretera gira a la izquierda tras el puente.",
        "Sigue... hasta la pequeña puerta de madera.",
        "Te esperaré al otro lado."
      ],
      "text": "La carretera gira a la izquierda tras el puente. Sigue... hasta la pequeña puerta de madera. Te esperaré al otro lado.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-2",
      "key": "de74ae45af89f36da09a4fed02a615f3415a5d4a09b0ddee806bfa39e66789e7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Te esperaré al otro lado.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f967e4ed0f942b4ac6490a866edc49e7af3b65b26d32f55ab4ff89967b39b6e0",
      "generation_seconds_batch": 18.445254555903375,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.575802803039551,
        "target_z": 0.23632821866963968,
        "ce": 6.260893821716309,
        "genuineness": 4.306513786315918,
        "identity": 0.5259957313537598,
        "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/de74ae45af89f36da09a4fed02a615f3415a5d4a09b0ddee806bfa39e66789e7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "df4821691727f33966bfc39fd2631773623043c72192e0fcf17932e4884a9a6c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "225e15d8b1baf73ff8e384ceba2d30e9fd8d226a25869f7292ebbfb12de177e2",
      "generation_seconds_batch": 23.97754695697222,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8326375484466553,
        "target_z": 1.2031250100296365,
        "ce": 6.165581703186035,
        "genuineness": 4.13078498840332,
        "identity": 0.5328764915466309,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.",
        "wer": 0.058823529411764705,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/df4821691727f33966bfc39fd2631773623043c72192e0fcf17932e4884a9a6c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "df900f36eabb495c14c9e9302955771fa212920134a1eaca9d8ddc651f57b4ae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "86c6ce86051d1b801b09497f52acb77ee9c6194f2cf636162de3b877435364da",
      "generation_seconds_batch": 23.37026508897543,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.133810997009277,
        "genuineness": 4.017816066741943,
        "identity": 0.5149896144866943,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/df900f36eabb495c14c9e9302955771fa212920134a1eaca9d8ddc651f57b4ae.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "dfda459211dd7df4111ae354914a862099b4e8a3df602899738d71c8e2399f9f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e15c1891a37c6c1dfc0447861a34fce945d29fd1e3bcd288d78216dbe38806a3",
      "generation_seconds_batch": 29.307012178003788,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.530099630355835,
        "target_z": 0.20117190168599677,
        "ce": 6.149696350097656,
        "genuineness": 4.055472373962402,
        "identity": 0.5843620300292969,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/dfda459211dd7df4111ae354914a862099b4e8a3df602899738d71c8e2399f9f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "e003ca0930842199c93cbd8e2375bb808dcd842f92a0e84c9dc52dbca7735ff4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a1932755817e418cdb22cd71a245e728430e79be7373676adfb4fc0b7319beb5",
      "generation_seconds_batch": 24.54388007707894,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.751387596130371,
        "target_z": 1.140624992835974,
        "ce": 5.9431867599487305,
        "genuineness": 3.6914620399475098,
        "identity": 0.25321292877197266,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e003ca0930842199c93cbd8e2375bb808dcd842f92a0e84c9dc52dbca7735ff4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e0601124cb6907aeb98b436a31b992953d5ee54c8c0b5bd5ae91108e1cacd57e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fab2819d0a47f3378a98671f95e1fca1ba9724c79b5cec7f31031b6d70bcf0c8",
      "generation_seconds_batch": 20.062782611930743,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.5279502868652344,
        "target_z": 0.9687499914031689,
        "ce": 6.205295085906982,
        "genuineness": 4.143336772918701,
        "identity": 0.7989598512649536,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e0601124cb6907aeb98b436a31b992953d5ee54c8c0b5bd5ae91108e1cacd57e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "e097bf813fb88ff810a8ad2f7506cbfc568ead9a67c7dcb97f2417340a472c70",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "05cfdc176378920d2d958453a0f61b8833f7c4fd9b1e336272df06c27f1bb462",
      "generation_seconds_batch": 25.09561674494762,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.599043846130371,
        "target_z": 1.0234373918232078,
        "ce": 6.117925643920898,
        "genuineness": 4.356721878051758,
        "identity": 0.6978853940963745,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e097bf813fb88ff810a8ad2f7506cbfc568ead9a67c7dcb97f2417340a472c70.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "e16869ba44498ca61b41fab18a262627909cd65b938c1a8a4c02bff8e1fe43b8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "67cafb0714924cdce990214cf599e89b5bccc872baa9e2a8c12e0a3be3264480",
      "generation_seconds_batch": 22.84294115693774,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.54826283454895,
        "target_z": 0.9843750415513507,
        "ce": 5.967014789581299,
        "genuineness": 4.13078498840332,
        "identity": 0.47644251585006714,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e16869ba44498ca61b41fab18a262627909cd65b938c1a8a4c02bff8e1fe43b8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "e1a26a2da22a5db5ec7a0f9cb08ceb38994c6c45824ec98f65d7251c0e481dc6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "44503d0f965058ab584898c7ebf1d2764288c5a885a55417af2e5811b67c4291",
      "generation_seconds_batch": 22.85638883896172,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.9646687507629395,
        "target_z": 1.3046875608942208,
        "ce": 6.197352409362793,
        "genuineness": 4.243753433227539,
        "identity": 0.584315836429596,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e1a26a2da22a5db5ec7a0f9cb08ceb38994c6c45824ec98f65d7251c0e481dc6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "e1c91a4bc152ca332389fd186c5843a90b41f6eb6f3857f7bd9f591369721ba0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "43ba72b9c5e88eddfd10ac903f98fc42fbf63724556988e3c894a8db97bd8604",
      "generation_seconds_batch": 23.09460685995873,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.005293846130371,
        "target_z": 1.3359376611905847,
        "ce": 6.213237762451172,
        "genuineness": 4.118232727050781,
        "identity": 0.6566709280014038,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e1c91a4bc152ca332389fd186c5843a90b41f6eb6f3857f7bd9f591369721ba0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e1d147313beaabd475057c000afbca68b2b14f54b53691b6bccdc920d1cd29e9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "19e20843afb583bb42f889ea25a25b6e7ab7d1a729080e56ab1bfa8f82a1d699",
      "generation_seconds_batch": 24.79015061701648,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.63498067855835,
        "target_z": 1.8203125651926364,
        "ce": 6.213237762451172,
        "genuineness": 4.306513786315918,
        "identity": 0.5208598375320435,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in.",
        "wer": 0.05555555555555555,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e1d147313beaabd475057c000afbca68b2b14f54b53691b6bccdc920d1cd29e9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "e1d93a23767968637e75a24211a009eaf4c291f76d83a1891a046104a49ac06b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "8b98e05ea44c65ab162dcf7c14e8f6b1dacec375676a7e4f11785d88c225b73d",
      "generation_seconds_batch": 18.43203284207266,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.030294418334961,
        "target_z": 0.5859374548666363,
        "ce": 6.252951145172119,
        "genuineness": 4.18726921081543,
        "identity": 0.7609533071517944,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e1d93a23767968637e75a24211a009eaf4c291f76d83a1891a046104a49ac06b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "e230623d80b8ee78faa2362caa988e2ec4012b09fb159d98c0104901a4a57746",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "26a2a181155852e0892415442df8467043c377065a53eb5fc70e9963923852aa",
      "generation_seconds_batch": 18.590096757980064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6802940368652344,
        "target_z": 1.0859375924159351,
        "ce": 5.752562999725342,
        "genuineness": 3.798154592514038,
        "identity": 0.5100808143615723,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e230623d80b8ee78faa2362caa988e2ec4012b09fb159d98c0104901a4a57746.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e23e567cfc254cd76a5cfc6ce9a2da28edb2eb9ac82ffe3c2ccaaec4c12236d2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "ea4b419bb0a90a9085744dd88c59ef7d5045e433d2684f0b19221dc23d79272b",
      "generation_seconds_batch": 20.07518050901126,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0883030891418457,
        "target_z": -0.13867188449233442,
        "ce": 6.252951145172119,
        "genuineness": 4.306513786315918,
        "identity": 0.6648117899894714,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e23e567cfc254cd76a5cfc6ce9a2da28edb2eb9ac82ffe3c2ccaaec4c12236d2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "e2b731323777aaba2ba5c3ec256d95b438b56143b19d1bf114935975ca95ec06",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6b4993e47eb5fa59cd33c970a339f393fb335a36426d05f07cecc1dadc7b3127",
      "generation_seconds_batch": 26.703512278036214,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1166224479675293,
        "target_z": 0.6523436887475779,
        "ce": 5.982900142669678,
        "genuineness": 4.143336772918701,
        "identity": 0.44631534814834595,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e2b731323777aaba2ba5c3ec256d95b438b56143b19d1bf114935975ca95ec06.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "e2e0bc2c16d64fabe24be2f5e9ccd1182d2edc662dc883617ada24cad93fa7b5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "88a53a3f0b91fcb0c45594b1152bb4efd676ca7f986d81dfd6c5078701f332c7",
      "generation_seconds_batch": 16.4739788119914,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9947476387023926,
        "target_z": 0.5585937546566169,
        "ce": 6.252951145172119,
        "genuineness": 4.413206577301025,
        "identity": 0.8063894510269165,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e2e0bc2c16d64fabe24be2f5e9ccd1182d2edc662dc883617ada24cad93fa7b5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e3400bea44025e2711a424892aba01d344584dcc96b169331d26398749c6b6dd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "f354edce9c1ea707699690ed66b50e630621fd80956d5782f6fc411fb5928473",
      "generation_seconds_batch": 23.261828650953248,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8123250007629395,
        "target_z": 1.1874999598814544,
        "ce": 6.284721851348877,
        "genuineness": 3.9676074981689453,
        "identity": 0.47522270679473877,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e3400bea44025e2711a424892aba01d344584dcc96b169331d26398749c6b6dd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e3581712828ff81ac2f8d9dea2ee8b9c0930a8aeefe939c5939b03670983b696",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "94b8810bd80f59d374df117b2e927b574c596b7f966b33dffb497412db7226a4",
      "generation_seconds_batch": 23.62180249299854,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2435755729675293,
        "target_z": 0.7500000229248831,
        "ce": 6.268836498260498,
        "genuineness": 4.042920112609863,
        "identity": 0.5885359644889832,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e3581712828ff81ac2f8d9dea2ee8b9c0930a8aeefe939c5939b03670983b696.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "e3cb3c89a178008434697f44e2cc235747ad6cd9b8e4d77538e5cae242901f34",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "ee1d73eb6049ed53909893f890fed743191f4b656e442eba86d25993d9bf5169",
      "generation_seconds_batch": 26.185742670088075,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.360372304916382,
        "target_z": 0.8398437403285649,
        "ce": 6.300607204437256,
        "genuineness": 3.948779582977295,
        "identity": 0.3229207694530487,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.",
        "wer": 0.0625,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e3cb3c89a178008434697f44e2cc235747ad6cd9b8e4d77538e5cae242901f34.mp3"
    },
    {
      "id": "heldout-en-1",
      "language": "en",
      "sentences": [
        "The keys are on the kitchen table.",
        "I checked the drawer... then looked beside the window.",
        "Take them with you when you leave."
      ],
      "text": "The keys are on the kitchen table. I checked the drawer... then looked beside the window. Take them with you when you leave.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-1",
      "key": "e3d4c3c9c261a4203f4cca0face89ee11512b34ef7634e75543f7b7edc56374e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The keys are on the kitchen table.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Take them with you when you leave.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4e6f759d705b70783791c857f03d69f0d9aa171a4c5a5022735a1c9777298ee4",
      "generation_seconds_batch": 18.820658784010448,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8119354248046875,
        "target_z": 0.41796885352017543,
        "ce": 6.38797664642334,
        "genuineness": 3.9801597595214844,
        "identity": 0.377127468585968,
        "hypothesis": "The keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e3d4c3c9c261a4203f4cca0face89ee11512b34ef7634e75543f7b7edc56374e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "e409c5e00831adb2a300ba84e51777f952521e2908f7a4a0e21049dfec5f3c32",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9b267dcab1198172e4e8cd1f75a8f3a2df242858364c185498cf4c909ade5a9b",
      "generation_seconds_batch": 24.23462665406987,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1978724002838135,
        "target_z": 0.7148437059412402,
        "ce": 6.133810997009277,
        "genuineness": 3.6412534713745117,
        "identity": 0.37190163135528564,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e409c5e00831adb2a300ba84e51777f952521e2908f7a4a0e21049dfec5f3c32.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "e475faf75c583425c6dd03d46063fd2b670089aeb18bac586496433932fef049",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "647b93eb91cba0375c82778d36f67f4cfe21be49531478fbb7b6d891db7a1100",
      "generation_seconds_batch": 24.692658704007044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.8123250007629395,
        "target_z": 1.1874999598814544,
        "ce": 6.252951145172119,
        "genuineness": 3.9299514293670654,
        "identity": 0.3279341459274292,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e475faf75c583425c6dd03d46063fd2b670089aeb18bac586496433932fef049.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e48cbe707a768f24f160a3f5e76fd44c7bba01070c4b92f2d5e4921f9c5c0125",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "35ea832b4e878d6c8206841d0bd818fd22ed68415f82f35ba5e14254a4a22529",
      "generation_seconds_batch": 27.290947637986392,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1013882160186768,
        "target_z": 0.6406250386857403,
        "ce": 6.316492557525635,
        "genuineness": 4.293961524963379,
        "identity": 0.6924101114273071,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e48cbe707a768f24f160a3f5e76fd44c7bba01070c4b92f2d5e4921f9c5c0125.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "e49c5fdf6b29e40f6842ecd27582fa47107aaf3ec11e0b0344be468e14be3073",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b8ebda38ee1fd9c5bf91142055ad49e58f8c5f1808138336eb7b943ce763ac3e",
      "generation_seconds_batch": 17.55791000497993,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9232641458511353,
        "target_z": -0.2656250272232987,
        "ce": 6.403861999511719,
        "genuineness": 4.174716949462891,
        "identity": 0.4919740855693817,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e49c5fdf6b29e40f6842ecd27582fa47107aaf3ec11e0b0344be468e14be3073.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "e4a846ffcbede20981e4ba04b773805670408e871d56a2fdaedd3c50ef674263",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1fad9674d6c28b17897466321cd58d2603fe6be40a44da2f5f83ccd6b1f4ca36",
      "generation_seconds_batch": 25.8522548309993,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.0709195137023926,
        "target_z": 0.6171875551630001,
        "ce": 5.982900142669678,
        "genuineness": 4.017816066741943,
        "identity": 0.3405851423740387,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4a846ffcbede20981e4ba04b773805670408e871d56a2fdaedd3c50ef674263.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "e4a9a016ef7fc60c7e01039ad5889b1b28a9a4c75603d77e827803d49d833d73",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c9312ff9d516593f2f47c8159c4bea44316fefa818445c122669179a6d6013b0",
      "generation_seconds_batch": 24.14466606604401,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0966997146606445,
        "target_z": 1.4062499283597403,
        "ce": 6.23706579208374,
        "genuineness": 4.444586753845215,
        "identity": 0.7984896898269653,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.",
        "wer": 0.3157894736842105,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4a9a016ef7fc60c7e01039ad5889b1b28a9a4c75603d77e827803d49d833d73.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "e4afa7e500b9a69a7ed9f79b5f1017b00589b240e8c42a96ecd7371f22dce3ae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cd1203f05038029833eae73ba3303c2e41f2b78959e4476be3cf4c7f752d426e",
      "generation_seconds_batch": 24.49260006507393,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.167793273925781,
        "target_z": 1.460937328779779,
        "ce": 6.078212261199951,
        "genuineness": 4.068024158477783,
        "identity": 0.5627614259719849,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4afa7e500b9a69a7ed9f79b5f1017b00589b240e8c42a96ecd7371f22dce3ae.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "e4e2eab23695eabb57d7f2f7753e73fa1462ed53fa751b8a7cd3730b0e8bd3c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ef888ad4454e70f94539d36e360eeeddafe63a1340c60b35d57199edaecf9b99",
      "generation_seconds_batch": 22.69549689500127,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.903731346130371,
        "target_z": 1.2578125938487403,
        "ce": 6.284721851348877,
        "genuineness": 4.017816066741943,
        "identity": 0.553887665271759,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4e2eab23695eabb57d7f2f7753e73fa1462ed53fa751b8a7cd3730b0e8bd3c9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "e4e31caa00b3899621b8643caf386589c5d409b39ac1cd802a580995d9a5ef97",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c3b70afa8fd1230b0b6e0bd2c5aa6cc3b96df2b9cf12c31b5771a044ebe6702a",
      "generation_seconds_batch": 23.68723886902444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.035372734069824,
        "target_z": 0.5898438549529806,
        "ce": 6.268836498260498,
        "genuineness": 4.149612903594971,
        "identity": 0.4112784266471863,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4e31caa00b3899621b8643caf386589c5d409b39ac1cd802a580995d9a5ef97.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "e4fff24a25dc712e9a6e5a3ba993405b6fe8f4ce88caa0ef1e7860182e504eef",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "f5ba2fe2b5a0a2dba9064aecdd89769074c137c44a845cf39cd4df130741978c",
      "generation_seconds_batch": 25.253876965958625,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.624824523925781,
        "target_z": 1.812500131818078,
        "ce": 6.062326908111572,
        "genuineness": 4.093128204345703,
        "identity": 0.5319560170173645,
        "hypothesis": "I've trouved the petite boîte. It is pretty fenêtre. We're going to be able to do that.",
        "wer": 0.8947368421052632,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e4fff24a25dc712e9a6e5a3ba993405b6fe8f4ce88caa0ef1e7860182e504eef.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "e5406549f550b1a1a393dbc19621cccf3981b3ffc0af10ba3fc0cf8e57690241",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "92575fad1fd9c991682b147415a736e0a7669c2aca7e1162b629566dd9f82aac",
      "generation_seconds_batch": 18.35334483999759,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6566628217697144,
        "target_z": -0.47070314559657467,
        "ce": 6.3641486167907715,
        "genuineness": 4.13078498840332,
        "identity": 0.4889437258243561,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e5406549f550b1a1a393dbc19621cccf3981b3ffc0af10ba3fc0cf8e57690241.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "e55a5567f4ac07e0adefae22d1372842f95a3d8cf3aa933eebfe55dd2d8e977d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cd698f2ccbe3e72261a5fa08db4a2027a7fb2ae42bd381debbea705ce8633cc3",
      "generation_seconds_batch": 24.120432006078772,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.208028793334961,
        "target_z": 0.7226563227148637,
        "ce": 6.078212261199951,
        "genuineness": 4.243753433227539,
        "identity": 0.6318167448043823,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e55a5567f4ac07e0adefae22d1372842f95a3d8cf3aa933eebfe55dd2d8e977d.mp3"
    },
    {
      "id": "heldout-fr-3",
      "language": "fr",
      "sentences": [
        "Quelqu’un a déplacé la petite chaise bleue.",
        "Elle était ici... près de la grande bibliothèque.",
        "Nous la remettrons après le déjeuner."
      ],
      "text": "Quelqu’un a déplacé la petite chaise bleue. Elle était ici... près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-3",
      "key": "e5c654804bad31110ac90210275e4255938f9ac64994dae626bb86bdfd3b1cff",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ae8fb1c6d5ed8bb0fa7b5006d967f42539fe6754ae5affdd77870c203e521c3a",
      "generation_seconds_batch": 18.355277181020938,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.72560715675354,
        "target_z": 0.35156243624016875,
        "ce": 6.078212261199951,
        "genuineness": 4.356721878051758,
        "identity": 0.6663776636123657,
        "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e5c654804bad31110ac90210275e4255938f9ac64994dae626bb86bdfd3b1cff.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e5ea395271d9d2ea692af591a115b118d601086323485ff39e38fb70731f2fbc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "eb0bcb391f248ab919e4237b59147d176bee2fe1b9b20a3d60dab7eb2dfc5989",
      "generation_seconds_batch": 24.53825893404428,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.269355773925781,
        "target_z": 1.5390623961216232,
        "ce": 6.133810997009277,
        "genuineness": 3.936227321624756,
        "identity": 0.6138576865196228,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e5ea395271d9d2ea692af591a115b118d601086323485ff39e38fb70731f2fbc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "e61a7e51a1b1bf82b1282812079f716557a351b509a0221a32ae752e2f273db7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ed68d004502425485ea0c3347e39ef94e161c7341c432a0eddc7ccacfda22ccb",
      "generation_seconds_batch": 16.584737755008973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.954122543334961,
        "target_z": 0.5273436543602532,
        "ce": 6.292664527893066,
        "genuineness": 4.482243061065674,
        "identity": 0.657054603099823,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e61a7e51a1b1bf82b1282812079f716557a351b509a0221a32ae752e2f273db7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "e6331b32ba9f77933fa2ba5ede26039e4ebf7499a6617fccacb59a5f4faadf72",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "cb7a8b20f73ed7723cb290c26a6c239c26273f03f2aec7aee87e31693aaf7373",
      "generation_seconds_batch": 25.999391563935205,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.340449333190918,
        "target_z": 1.5937497965416623,
        "ce": 5.863759994506836,
        "genuineness": 3.923675537109375,
        "identity": 0.2837015390396118,
        "hypothesis": "En que he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que ha hecho.",
        "wer": 0.23529411764705882,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e6331b32ba9f77933fa2ba5ede26039e4ebf7499a6617fccacb59a5f4faadf72.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "e67874636ecec603248f832a0833740972905cd14f6574801962aee86a872629",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "1ff5f20bb858448a91ac328c281ca047bf34f26433cb1fa864c96fd50c212d61",
      "generation_seconds_batch": 24.03445187304169,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 5.990842819213867,
        "genuineness": 4.287685871124268,
        "identity": 0.7499329447746277,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e67874636ecec603248f832a0833740972905cd14f6574801962aee86a872629.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Someone moved the little blue chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "e7d270ad350f1b0ed1592ec4eca47ddf73b138d151b0c9645b066ba987d99be9",
      "generation_seconds_batch": 18.039080351009034,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7658424377441406,
        "target_z": -0.3867187532238117,
        "ce": 6.324435234069824,
        "genuineness": 4.331617832183838,
        "identity": 0.3132067620754242,
        "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "e713bd8d17fa4b60f9ac61020911c0e275398d64f76c7ea367838479c6e2326a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0972262243927aeacea7d2c574774eb185dc21945637a16693a5e09a56444174",
      "generation_seconds_batch": 26.14291791000869,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2295384407043457,
        "target_z": -0.030029212720082316,
        "ce": 6.181467056274414,
        "genuineness": 4.162164688110352,
        "identity": 0.4911765158176422,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e713bd8d17fa4b60f9ac61020911c0e275398d64f76c7ea367838479c6e2326a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "e75117a8d9dd369fb866847225561037e26ffe0de2378d0fb2d3976513ac8b59",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "bf5641aaaf973640f1847fe7847d3df74070273ebbc30246e613f2b3156e75fa",
      "generation_seconds_batch": 16.911234361934476,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.0966997146606445,
        "target_z": 1.4062499283597403,
        "ce": 6.078212261199951,
        "genuineness": 4.168440818786621,
        "identity": 0.6190105676651001,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e75117a8d9dd369fb866847225561037e26ffe0de2378d0fb2d3976513ac8b59.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "e75375b8267e1de9d08a58c5a8f10b46ce8990c77dae38eaa9aa8d51003b2678",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ded206306b0c737081ef2f5df37bee57025183017fc4bf217b709b5801e585c4",
      "generation_seconds_batch": 17.913794555002823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9947476387023926,
        "target_z": 0.5585937546566169,
        "ce": 6.173524379730225,
        "genuineness": 4.300237655639648,
        "identity": 0.49655425548553467,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e75375b8267e1de9d08a58c5a8f10b46ce8990c77dae38eaa9aa8d51003b2678.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "e7a646faf861692384ca9858a0e9b763c7064f07d82b35d3c8e4dab10bd7f01b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "cf8497b0ba8af7a9bbac16a1b2e49ed6223fe12ab99069fff3656b985fa281c9",
      "generation_seconds_batch": 26.842566380044445,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2740442752838135,
        "target_z": 0.7734375064476234,
        "ce": 6.3641486167907715,
        "genuineness": 3.9550557136535645,
        "identity": 0.43468746542930603,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e7a646faf861692384ca9858a0e9b763c7064f07d82b35d3c8e4dab10bd7f01b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "e7c25227f15a9e30c8b32f1d99b0fadf9cf1b5cc69f2ee534fb6ec3a33a73ce9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "148f5b9e47a19ce0fcc3585255662ab98341e5500eae4f7341457aba232e10e7",
      "generation_seconds_batch": 24.06138741201721,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.49748158454895,
        "target_z": 0.9453125078804285,
        "ce": 6.0305562019348145,
        "genuineness": 3.9550557136535645,
        "identity": 0.5268285274505615,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e7c25227f15a9e30c8b32f1d99b0fadf9cf1b5cc69f2ee534fb6ec3a33a73ce9.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "e7df7a60249def89cccbf0be7e56c8b09fea7c4d07760ac249118ee8bd25eceb",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "de830f0f67e9f0cfd5cb31e3084d5283585bb8593d26a772d70d2ec2587ac852",
      "generation_seconds_batch": 21.415874387021177,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.90334153175354,
        "target_z": 0.48828130408839615,
        "ce": 6.252951145172119,
        "genuineness": 4.400654315948486,
        "identity": 0.6239142417907715,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e7df7a60249def89cccbf0be7e56c8b09fea7c4d07760ac249118ee8bd25eceb.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "e82e1a1e0e1e5287150f80508f25de7a1bfcf4a1e662ad708effde03763204f5",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "451528d6ee2e8fbbb76f269cbd73d906737aa1e6f4739f88aab9ab98ea10199e",
      "generation_seconds_batch": 24.568017804063857,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6802940368652344,
        "target_z": 1.0859375924159351,
        "ce": 6.133810997009277,
        "genuineness": 4.18726921081543,
        "identity": 0.6287312507629395,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e82e1a1e0e1e5287150f80508f25de7a1bfcf4a1e662ad708effde03763204f5.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "e8ca8a6e6f2e2f145dc3b6196253c73640b5cdb2e1be956a267c68804d2ac6f4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "5df192942dd2948ddad4879d1741eca1361b816d929961621894e437f0579a90",
      "generation_seconds_batch": 23.869801393942907,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.619356632232666,
        "target_z": 1.0390626253704547,
        "ce": 6.125868320465088,
        "genuineness": 4.300237655639648,
        "identity": 0.5376290082931519,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e8ca8a6e6f2e2f145dc3b6196253c73640b5cdb2e1be956a267c68804d2ac6f4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "e8cfdfb6680cda92d089d40e982b0bed42f4d4149c8e122fa96198feda017fcc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ea94a1b4fa7dcd2768762912dec1ae51079879f84336f197682793c9e84fb36b",
      "generation_seconds_batch": 18.342360563925467,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.241281509399414,
        "target_z": -0.020996075168307614,
        "ce": 6.109982967376709,
        "genuineness": 4.293961524963379,
        "identity": 0.5797795653343201,
        "hypothesis": "The convelay to bin. J'ai trouvé la petite boat. Elle était prêt de la vie fenêtre.",
        "wer": 0.7368421052631579,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e8cfdfb6680cda92d089d40e982b0bed42f4d4149c8e122fa96198feda017fcc.mp3"
    },
    {
      "id": "heldout-en-0",
      "language": "en",
      "sentences": [
        "Your message arrived after I had left.",
        "I read it twice... before putting the phone away.",
        "Let me know when we can talk."
      ],
      "text": "Your message arrived after I had left. I read it twice... before putting the phone away. Let me know when we can talk.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-0",
      "key": "e8fe55a8876b84a3859d27c3a3c4803d998532a4f7663f1cd6c4dbb13c441cd8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Your message arrived after I had left.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Let me know when we can talk.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "e7b90dd4d2277236ac7d28a9fdfc8caefb80c70f1a4e5aaeef62fb7dedc2eecc",
      "generation_seconds_batch": 18.48575787700247,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5529510974884033,
        "target_z": 0.21874996847828568,
        "ce": 6.507116317749023,
        "genuineness": 4.18726921081543,
        "identity": 0.3882223963737488,
        "hypothesis": "Your message arrived after I had left. I read it twice before putting the phone away. Let me know when we can talk.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e8fe55a8876b84a3859d27c3a3c4803d998532a4f7663f1cd6c4dbb13c441cd8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "e9a19b9f91cdc5cc2665077e7147646ee27cb5a2857d8c8397708fd2c96888ae",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "db815345048ae86c486d66927b0a2bce62398db8e9cbca256548b6277a4de0e2",
      "generation_seconds_batch": 24.43924632598646,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.645136833190918,
        "target_z": 1.8281249985671948,
        "ce": 6.1020402908325195,
        "genuineness": 4.218649387359619,
        "identity": 0.5062336921691895,
        "hypothesis": "I've tried the petite boat. It is pretty fenêtre. We've read what.",
        "wer": 0.8947368421052632,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e9a19b9f91cdc5cc2665077e7147646ee27cb5a2857d8c8397708fd2c96888ae.mp3"
    },
    {
      "id": "heldout-en-2",
      "language": "en",
      "sentences": [
        "The road turns left behind the bridge.",
        "Keep going... until you reach the small wooden gate.",
        "I will meet you on the other side."
      ],
      "text": "The road turns left behind the bridge. Keep going... until you reach the small wooden gate. I will meet you on the other side.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-2",
      "key": "e9c8c912411974321c6658115523a4b1aed50dc41a3a9bcbbd9d9b03ae0acbec",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The road turns left behind the bridge.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I will meet you on the other side.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2bfcd716cc930ce8273d4b12a3d707f39e333de1dba8fa188611d078606d1414",
      "generation_seconds_batch": 16.36648829909973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1035375595092773,
        "target_z": -0.12695305103143176,
        "ce": 6.4912309646606445,
        "genuineness": 4.105680465698242,
        "identity": 0.24901816248893738,
        "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e9c8c912411974321c6658115523a4b1aed50dc41a3a9bcbbd9d9b03ae0acbec.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b026574d4b8f698ed00b23b3769a13d3f5e0505304523eb2078ad4c57f2e5f72",
      "generation_seconds_batch": 18.10996663500555,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8217017650604248,
        "target_z": -0.3437500028656104,
        "ce": 6.427689552307129,
        "genuineness": 4.319066047668457,
        "identity": 0.3824930489063263,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "ea1665ddba493a96997fa2e39440652c1efd8bd172aabfe426fb75a7a3dcdea7",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "325878497de1f60c18bd8d0503f26fdd328cd6b0e61bbbc310fda5d4d918fe87",
      "generation_seconds_batch": 26.93076340202242,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.306027412414551,
        "target_z": 0.028808508542866002,
        "ce": 6.316492557525635,
        "genuineness": 3.8671910762786865,
        "identity": 0.581969141960144,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ea1665ddba493a96997fa2e39440652c1efd8bd172aabfe426fb75a7a3dcdea7.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "ea5ba4deee41fc6a0aa230fe9e43a8c7af3b7aacc00102f60410fc948e9010bd",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "edd8a38e69d62637649e510354cbd5aeb99ceedc3f3d0fb79b9a7a8a8e3a8a35",
      "generation_seconds_batch": 17.470073992968537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.385762929916382,
        "target_z": 0.8593750071640259,
        "ce": 6.0305562019348145,
        "genuineness": 4.231201171875,
        "identity": 0.4720379412174225,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ea5ba4deee41fc6a0aa230fe9e43a8c7af3b7aacc00102f60410fc948e9010bd.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "ea80b584cf62fda581ed96523fc04abb02df89cbc246d35112ecca5f0cae24a0",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "b6e8d79e8acc238126abc002460c57fbc2b0b7bcb0ca6d37e1817e3212d18d56",
      "generation_seconds_batch": 24.763327075983398,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.726387023925781,
        "target_z": 1.8906251991599223,
        "ce": 5.911416053771973,
        "genuineness": 3.7416701316833496,
        "identity": 0.396640419960022,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ea80b584cf62fda581ed96523fc04abb02df89cbc246d35112ecca5f0cae24a0.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "eaaf163afe88a7a534cd9215e917043970614258291c6ff813e40ec32b513784",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "596f5b191828429a2b805b35ff05a0d298023fe26678ef34d9de18fcfe31e00a",
      "generation_seconds_batch": 26.00134980492294,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.416231632232666,
        "target_z": 0.8828124906867663,
        "ce": 6.1894097328186035,
        "genuineness": 4.482243061065674,
        "identity": 0.6203281879425049,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/eaaf163afe88a7a534cd9215e917043970614258291c6ff813e40ec32b513784.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "eb132894e6e95a3929c58cb70f844804092ec09d24bba87855e71d4aa142056c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "6e6b1a5fb4f2eb6ae2aca4838a46c2dbc225efd154a23a16befa3136e8fa19ca",
      "generation_seconds_batch": 25.65415217494592,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.7920126914978027,
        "target_z": 1.1718750931323378,
        "ce": 6.2767791748046875,
        "genuineness": 3.8546390533447266,
        "identity": 0.3066490888595581,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/eb132894e6e95a3929c58cb70f844804092ec09d24bba87855e71d4aa142056c.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "b91e56c40f5cd23651e3df34f479411fa7f1d9ff3fbecb3f3bd60560deb14154",
      "generation_seconds_batch": 19.34534896200057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.364670991897583,
        "target_z": -0.6953124391057792,
        "ce": 6.078212261199951,
        "genuineness": 4.369274139404297,
        "identity": 0.7732385993003845,
        "hypothesis": "La route tourne à gauche après le pont. Continue. Jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "ebeee38cd3f75c1b09a767b4a9d18e85ca472ce5a10c386b42a0d742d7d9f7b6",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4a68ed0f41f910d2e52d0ee1f4fc2350d1bdf8cf748c5b6e8228196347837a44",
      "generation_seconds_batch": 24.389694404089823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9715063571929932,
        "target_z": -0.22851560189601622,
        "ce": 6.467403411865234,
        "genuineness": 3.9550557136535645,
        "identity": 0.35179927945137024,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ebeee38cd3f75c1b09a767b4a9d18e85ca472ce5a10c386b42a0d742d7d9f7b6.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "ebf31fac1b279a43fd9ca319146d54749406ec705a6704284f45771952f4ce19",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "0509402c399a632f45e18e5cad287d34362662ef4d49132a5ebceb4c3a4d3383",
      "generation_seconds_batch": 22.37469820503611,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 5.752562999725342,
        "genuineness": 3.6287014484405518,
        "identity": 0.37317126989364624,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lembrando.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ebf31fac1b279a43fd9ca319146d54749406ec705a6704284f45771952f4ce19.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "ec33a8c23c9adb0e516d8a5dcee12d071ea93a9fa33c4f0c30201f50f83d8a61",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 132,
      "seconds_generated": 10.56,
      "mp3_sha256": "f7569d63811a4eca07b603b1e86693b424d33d650ab6adb88b92f4231a880c99",
      "generation_seconds_batch": 28.81426474894397,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.771700143814087,
        "target_z": 1.1562500429841558,
        "ce": 5.617537498474121,
        "genuineness": 3.565941095352173,
        "identity": 0.427340030670166,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo es.",
        "wer": 0.13333333333333333,
        "duration_error_s": 0.3600000000000012,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ec33a8c23c9adb0e516d8a5dcee12d071ea93a9fa33c4f0c30201f50f83d8a61.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "ec53e8c70be8874b9e391cba063ed1567c8f11aaf85a70997f366793284a1ae4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f31cabb49147dd00e3c50e87e7647cce8352fb75e9fc6ac8e42d76c61d0b43e6",
      "generation_seconds_batch": 24.00645129790064,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.848261833190918,
        "target_z": 1.9843751332508832,
        "ce": 6.205295085906982,
        "genuineness": 4.1998209953308105,
        "identity": 0.37743258476257324,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ec53e8c70be8874b9e391cba063ed1567c8f11aaf85a70997f366793284a1ae4.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "ec648aacffc9393e59b9aa7d4b2465af834cc6910b6b02401dc15ebcf4318d06",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "20ff3c8222f47526edbe78461364887fa20ed9591e05e48f61d878e79c34e24d",
      "generation_seconds_batch": 16.52717118896544,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7252174615859985,
        "target_z": -0.41796876182064285,
        "ce": 6.403861999511719,
        "genuineness": 4.632867813110352,
        "identity": 0.5549097061157227,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ec648aacffc9393e59b9aa7d4b2465af834cc6910b6b02401dc15ebcf4318d06.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "ecb1efab3d0de6538ceb79a573dd8365a310633ae16f77efe5eb37becdaeab62",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d0cd1fd717666e0ea7ef0f512abe569daa921cf7a8996d3dc0311a14f6b518a0",
      "generation_seconds_batch": 24.46885795390699,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.4009971618652344,
        "target_z": 0.8710936572258635,
        "ce": 5.959072113037109,
        "genuineness": 3.810706615447998,
        "identity": 0.6639325618743896,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ecb1efab3d0de6538ceb79a573dd8365a310633ae16f77efe5eb37becdaeab62.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "eda4d39c546a1d6709dc1ca86e3bc70330a784b5b137e9257daa8812d00de762",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4568a37f505b74f5d379824cb206411ff4d9ef240a3f9f9b882ba211b851f2d5",
      "generation_seconds_batch": 23.79733815405052,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.908419609069824,
        "target_z": 0.49218752077567535,
        "ce": 6.459460258483887,
        "genuineness": 4.137060642242432,
        "identity": 0.6119006872177124,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/eda4d39c546a1d6709dc1ca86e3bc70330a784b5b137e9257daa8812d00de762.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "edf7ac2999aa08ff04e6d96c223f3395556d1a4935f696da74e4bae54829e420",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7da9bddf4e0d9adee616bf3469822196e2f83eebe8908479982eeaeb1190d6c0",
      "generation_seconds_batch": 23.87746356392745,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.035762310028076,
        "target_z": 1.3593749613142596,
        "ce": 6.348263263702393,
        "genuineness": 3.9048471450805664,
        "identity": 0.5014318227767944,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/edf7ac2999aa08ff04e6d96c223f3395556d1a4935f696da74e4bae54829e420.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "ee2c1bc818088dfaaa46367730d9264ee7c542e9f4473f2e223bd9f1e5aa0811",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "62f2c94449eb5a2a2a472da0498193c71fd998915fe0d85001a1129e677d4689",
      "generation_seconds_batch": 24.54117157298606,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.852950096130371,
        "target_z": 1.2187500601778183,
        "ce": 6.109982967376709,
        "genuineness": 4.193545341491699,
        "identity": 0.6452752351760864,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ee2c1bc818088dfaaa46367730d9264ee7c542e9f4473f2e223bd9f1e5aa0811.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "ee8117bffab725ac0d1d045b93c034dc6a202fdb9560db3ae76cac060aa6e2d8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "fbeff17269a008f0f17d8621cc4bbcde95b39f081ab0318724a6f33af2a004a8",
      "generation_seconds_batch": 23.124252639943734,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1013882160186768,
        "target_z": 0.6406250386857403,
        "ce": 6.356205940246582,
        "genuineness": 4.2751336097717285,
        "identity": 0.3883174657821655,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ee8117bffab725ac0d1d045b93c034dc6a202fdb9560db3ae76cac060aa6e2d8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "ee84f6e52e78c10ffd9cb256852cc150c8486003c5efd8bbef22f35cf1c4e73b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "wording",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "74ed3e2448671b6ae4e57308fa55aa98c823d7cba661d38ee3397a4325e9ebaa",
      "generation_seconds_batch": 17.88839563005604,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.7865447998046875,
        "target_z": 0.39843758668471435,
        "ce": 6.23706579208374,
        "genuineness": 3.8922953605651855,
        "identity": 0.25175604224205017,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ee84f6e52e78c10ffd9cb256852cc150c8486003c5efd8bbef22f35cf1c4e73b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "ef6375c3987eb2233ee38a6a4ac219969f614ca2c5676e3c0a13248c4ea8f27d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "20264caeff94f0aa402d321644f1e998a528b4dc5be635d91b629e4308548739",
      "generation_seconds_batch": 18.817335570929572,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.751387596130371,
        "target_z": 1.140624992835974,
        "ce": 6.149696350097656,
        "genuineness": 4.030367851257324,
        "identity": 0.6634243726730347,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ef6375c3987eb2233ee38a6a4ac219969f614ca2c5676e3c0a13248c4ea8f27d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "ef89d2746e8e97531d591f2bc4f36017e94bb985c2ff2d2edcbefd3fa96ccd51",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3e70eb75bb58ca1fcedb5950527c97802f785740f2d7194c8621f39ac3998774",
      "generation_seconds_batch": 23.876020852010697,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.954122543334961,
        "target_z": 0.5273436543602532,
        "ce": 6.173524379730225,
        "genuineness": 3.8420867919921875,
        "identity": 0.32320305705070496,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ef89d2746e8e97531d591f2bc4f36017e94bb985c2ff2d2edcbefd3fa96ccd51.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "efb3b66ec7b710acc008b748b13d51ed9c38ea41e101319af44c1c820407bb49",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "713d0fbea5a2937d520feea86d7d5c9fa0e83fc6fd08cb5a60fd6dc58f320a55",
      "generation_seconds_batch": 22.59376187401358,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.035372734069824,
        "target_z": 0.5898438549529806,
        "ce": 5.8875885009765625,
        "genuineness": 3.6789097785949707,
        "identity": 0.4066579043865204,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/efb3b66ec7b710acc008b748b13d51ed9c38ea41e101319af44c1c820407bb49.mp3"
    },
    {
      "id": "heldout-nl-3",
      "language": "nl",
      "sentences": [
        "Iemand heeft het kleine blauwe stoeltje verplaatst.",
        "Het stond hier... naast de hoge boekenkast.",
        "We zetten het na de lunch terug."
      ],
      "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-3",
      "key": "f07d4f42148ceb4c57027bc7372f684a6ce512313e99f877e0ac5ea1bb95124c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "28cd9fc58a6c6115a93459ee537202b0fd68ef2cb121183509bb85c8064bcd85",
      "generation_seconds_batch": 23.05104724492412,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.8754117488861084,
        "target_z": 0.46679683720976295,
        "ce": 6.308549880981445,
        "genuineness": 4.18099308013916,
        "identity": 0.7292183041572571,
        "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunch terug.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f07d4f42148ceb4c57027bc7372f684a6ce512313e99f877e0ac5ea1bb95124c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "f08069d7abe00aff5eabb3ea0c99acfb103a365218ce1dc559319f0bce05c361",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "7c92e22a7ec73de9cfc840ed80d3ff8fe4f078288cd973913e01cc04a64cdee1",
      "generation_seconds_batch": 24.087617627927102,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.467012882232666,
        "target_z": 0.9218750243576883,
        "ce": 5.4666266441345215,
        "genuineness": 3.5596652030944824,
        "identity": 0.10082611441612244,
        "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen.",
        "wer": 0.1111111111111111,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f08069d7abe00aff5eabb3ea0c99acfb103a365218ce1dc559319f0bce05c361.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "f083e2abacba234497465a185aaf19c96d8fd31e21dae661f2fcb83b25d492f3",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "02146278cbf85ef34088444b35dfee42a7281f462df0d13d07fd7c10dc3fc4f3",
      "generation_seconds_batch": 32.48298022907693,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.330293655395508,
        "target_z": 1.585937729965234,
        "ce": 5.601652145385742,
        "genuineness": 3.565941095352173,
        "identity": 0.34191882610321045,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f083e2abacba234497465a185aaf19c96d8fd31e21dae661f2fcb83b25d492f3.mp3"
    },
    {
      "id": "heldout-en-3",
      "language": "en",
      "sentences": [
        "Someone moved the little blue chair.",
        "It used to stand here... beside the tall bookshelf.",
        "We can put it back after lunch."
      ],
      "text": "Someone moved the little blue chair. It used to stand here... beside the tall bookshelf. We can put it back after lunch.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-en-3",
      "key": "f0e060eb267ce3d28f98246e7ec8bcc042c1646cb57ffb727622cb524df266b9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Someone moved the little blue chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can put it back after lunch.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "3d3a58d63e38f689ca61e652d88f98c35be8976d3034534c4739c1c74cd157a7",
      "generation_seconds_batch": 20.554392135934904,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.27746319770813,
        "target_z": 0.006836016752037403,
        "ce": 6.459460258483887,
        "genuineness": 4.2751336097717285,
        "identity": 0.32035398483276367,
        "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. We can put it back after lunch.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f0e060eb267ce3d28f98246e7ec8bcc042c1646cb57ffb727622cb524df266b9.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "f0f8c7c2a0d562c38a0d3f1bc518d47603db519523d5ed05852de298b7fd8e58",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "771f37e3ed5fee1f9fd40782328754bdab8d4b1398c87858a619f15b65b4091a",
      "generation_seconds_batch": 24.367143192095682,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2943568229675293,
        "target_z": 0.7890625565958053,
        "ce": 6.221180438995361,
        "genuineness": 4.262581825256348,
        "identity": 0.5578504800796509,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f0f8c7c2a0d562c38a0d3f1bc518d47603db519523d5ed05852de298b7fd8e58.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "f136f20abafd3999117d09c55383228225afdb7be7412aaeb5950ebe983a13e2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 126,
      "seconds_generated": 10.08,
      "mp3_sha256": "59dc2fd8fd814ccbe28d6c5d3aa833ddc8da91844157611e655dcf0cad602cf2",
      "generation_seconds_batch": 24.413228293065913,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1217007637023926,
        "target_z": 0.6562500888339221,
        "ce": 5.6413655281066895,
        "genuineness": 4.005263805389404,
        "identity": 0.1662026047706604,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je komt.",
        "wer": 0.10526315789473684,
        "duration_error_s": 0.11999999999999922,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f136f20abafd3999117d09c55383228225afdb7be7412aaeb5950ebe983a13e2.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "f15162221121a3f2560bc2bbb6d81c9773dd4fac945046072d4bf526b4b1b4e1",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a25255e192c353b3b249bdd9226d910bb15f8c1887dee9262a16ffb93ddf396f",
      "generation_seconds_batch": 16.52717118896544,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3371310234069824,
        "target_z": 0.05273438377593183,
        "ce": 6.419747352600098,
        "genuineness": 4.419482707977295,
        "identity": 0.4347487688064575,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f15162221121a3f2560bc2bbb6d81c9773dd4fac945046072d4bf526b4b1b4e1.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "f153738989645da49e125bea120a103bb5d78a4701db147bf4df2869fe6d74e4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "6002c78dd944fb856ac967d9ad184247bedc9a1fc154e8703130b47276db1eba",
      "generation_seconds_batch": 24.306299900985323,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.233419418334961,
        "target_z": 0.7421875895503247,
        "ce": 6.09409761428833,
        "genuineness": 4.111956596374512,
        "identity": 0.6043189764022827,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f153738989645da49e125bea120a103bb5d78a4701db147bf4df2869fe6d74e4.mp3"
    },
    {
      "id": "heldout-fr-0",
      "language": "fr",
      "sentences": [
        "Ton message est arrivé après mon départ.",
        "Je l’ai relu... puis j’ai rangé mon téléphone.",
        "Dis-moi quand nous pourrons parler."
      ],
      "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-0",
      "key": "f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "20e691267400655421c44ee32bc86494895bbd474c4f6bdc21702a93ffde1525",
      "generation_seconds_batch": 18.01340800698381,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6769752502441406,
        "target_z": -0.45507818714792536,
        "ce": 6.109982967376709,
        "genuineness": 4.331617832183838,
        "identity": 0.7347861528396606,
        "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "f26260bddfe1c9a3938412bd76676f8b2dbf7eeb24bec729512f7d795fbbaa59",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "56e737d778c5986f74102d863e1974d1098faefb3e62a3b132880016987e2ca4",
      "generation_seconds_batch": 23.956173336016946,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7176003456115723,
        "target_z": -0.42382808685156165,
        "ce": 6.38797664642334,
        "genuineness": 4.293961524963379,
        "identity": 0.6444124579429626,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f26260bddfe1c9a3938412bd76676f8b2dbf7eeb24bec729512f7d795fbbaa59.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "f27225041826d516aa7750275110c1c3cd70f271bb8c85dc4c1f99468ccdb49d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "d62cf48a243f2252be6c5d0c2ab70f95e070f29207ae1616e09af17ed1a15429",
      "generation_seconds_batch": 16.688994994037785,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4279024600982666,
        "target_z": 0.12255862603289207,
        "ce": 6.300607204437256,
        "genuineness": 4.005263805389404,
        "identity": 0.52276611328125,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f27225041826d516aa7750275110c1c3cd70f271bb8c85dc4c1f99468ccdb49d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "f32f3187e51896c148308c18d422d1392f169a9215d56f8036c6ef1304c0755d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 130,
      "seconds_generated": 10.4,
      "mp3_sha256": "a0e150281d986aae5ff2afce342c52fa8a71dfb79875945eb423ef64a70743fe",
      "generation_seconds_batch": 28.81426474894397,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.2998247146606445,
        "target_z": 1.5625000630434287,
        "ce": 5.796247482299805,
        "genuineness": 3.6914620399475098,
        "identity": 0.27609533071517944,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás.",
        "wer": 0.13333333333333333,
        "duration_error_s": 0.20000000000000107,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f32f3187e51896c148308c18d422d1392f169a9215d56f8036c6ef1304c0755d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "f36d204b328086d31787f4f6d1f5a19f4965a19378504ee27198851d5f1908e2",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "ff682180253e2f55480d508be9ed6f5b1919b9bad02b93e82e110c4ce7480927",
      "generation_seconds_batch": 23.385041343979537,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.334981679916382,
        "target_z": 0.8203124734931039,
        "ce": 6.181467056274414,
        "genuineness": 4.15588903427124,
        "identity": 0.5788347721099854,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f36d204b328086d31787f4f6d1f5a19f4965a19378504ee27198851d5f1908e2.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "f38380a9cb257d6ccf14885d752ab6dd9ae9cfba85d15da045a71e1523805326",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "8d5d60e0489392d4c90ba11ba5c34c22adb90978c035926cbe4485e2b55d78b9",
      "generation_seconds_batch": 29.48329180595465,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.289278507232666,
        "target_z": 0.7851561565094609,
        "ce": 5.831989288330078,
        "genuineness": 3.986435890197754,
        "identity": 0.48478201031684875,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f38380a9cb257d6ccf14885d752ab6dd9ae9cfba85d15da045a71e1523805326.mp3"
    },
    {
      "id": "heldout-es-4",
      "language": "es",
      "sentences": [
        "Escribí el número en el sobre.",
        "Léelo bien... y comprueba las dos últimas cifras.",
        "Llámame cuando tengas un momento."
      ],
      "text": "Escribí el número en el sobre. Léelo bien... y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-4",
      "key": "f38d109b875fcb4aae3b7117fa293861e115628a8266489264130b4a9568111c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Escribí el número en el sobre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "c594e738b9c31b5685433018bdb8ea5aed3fc52f4980ef2d0e5276df556b3c96",
      "generation_seconds_batch": 19.161313239019364,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.149240493774414,
        "target_z": -0.09179691744685393,
        "ce": 6.332377910614014,
        "genuineness": 4.432034492492676,
        "identity": 0.7183555364608765,
        "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f38d109b875fcb4aae3b7117fa293861e115628a8266489264130b4a9568111c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "f394bacbfe54a05b7540be7a4613d03691d6206880e60536a40bc663d9bb0c9e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "a4ee674d06a520e91425a61e70ba7de12ef6f1d7885091fddc5aa1b3de328891",
      "generation_seconds_batch": 26.72725272795651,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.599043846130371,
        "target_z": 1.0234373918232078,
        "ce": 6.173524379730225,
        "genuineness": 3.575355052947998,
        "identity": 0.4794238805770874,
        "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0625,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f394bacbfe54a05b7540be7a4613d03691d6206880e60536a40bc663d9bb0c9e.mp3"
    },
    {
      "id": "heldout-nl-1",
      "language": "nl",
      "sentences": [
        "De sleutels liggen op de keukentafel.",
        "Ik keek in de la... en daarna naast het raam.",
        "Neem ze mee als je weggaat."
      ],
      "text": "De sleutels liggen op de keukentafel. Ik keek in de la... en daarna naast het raam. Neem ze mee als je weggaat.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-nl-1",
      "key": "f3ef67fb93622b157de23a6bc37e5185ae72e9c30e860a55145b64159d2f7841",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "7db565a22e4320aa74fc92a78eaef678d0cdc8978aa3ff5832435f60c6604591",
      "generation_seconds_batch": 18.69971864297986,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2184300422668457,
        "target_z": -0.038574141960596525,
        "ce": 6.213237762451172,
        "genuineness": 4.18099308013916,
        "identity": 0.47316426038742065,
        "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f3ef67fb93622b157de23a6bc37e5185ae72e9c30e860a55145b64159d2f7841.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "f46145760e6ac85da0843bf7b5216806200b39aef657aed693618e2f8e756b87",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "98787d443869312ed5b50c8757445bf2fbdbf859aa5c8f163bd326c21fb933fe",
      "generation_seconds_batch": 24.597534175030887,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.117925643920898,
        "genuineness": 4.218649387359619,
        "identity": 0.4543069005012512,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f46145760e6ac85da0843bf7b5216806200b39aef657aed693618e2f8e756b87.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "f463e4787dbf1423d79ef2f21370234c04dbd60d68e66422171700c14d50b4dc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "709f79bc954e677655d7205151f6270e9b123578d30064a33437b33975cf12cb",
      "generation_seconds_batch": 24.389694404089823,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.130197525024414,
        "target_z": -0.10644536757344972,
        "ce": 6.395919322967529,
        "genuineness": 4.099404335021973,
        "identity": 0.5437659025192261,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f463e4787dbf1423d79ef2f21370234c04dbd60d68e66422171700c14d50b4dc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "f46adda726493ecacf1b6b7d410a3ad2d9e5f0c94104e4a47df118d43cea7045",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "566d1d820c1792d77785308669a780f27dca520e5fbefac2713b21378d74a568",
      "generation_seconds_batch": 24.244613928021863,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.289278507232666,
        "target_z": 0.7851561565094609,
        "ce": 5.593709468841553,
        "genuineness": 3.7793264389038086,
        "identity": 0.5099011659622192,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f46adda726493ecacf1b6b7d410a3ad2d9e5f0c94104e4a47df118d43cea7045.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "f47ebb4120a917409bbdbfb684c207cd603ed76e31739d8b8d52c1a9d0ef2516",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "61fe956b0fc8b6f4fa3cd238e45169506ff8c39d1dda2616c018cb8b85c9d25b",
      "generation_seconds_batch": 26.14291791000869,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.6599814891815186,
        "target_z": 1.0703125422677533,
        "ce": 6.292664527893066,
        "genuineness": 4.21237325668335,
        "identity": 0.6951171159744263,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f47ebb4120a917409bbdbfb684c207cd603ed76e31739d8b8d52c1a9d0ef2516.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "f5ba345f6ba3cac959860d5aa5095dcbecd4ad5e6bb8128a371ab7a58af6080a",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d6e6e69743144d1bc100113c87b862fffac3646a86b66c3485a61dc2bc39b5eb",
      "generation_seconds_batch": 17.64175843098201,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.111544370651245,
        "target_z": 0.6484374720602987,
        "ce": 5.9431867599487305,
        "genuineness": 4.036643981933594,
        "identity": 0.4549652338027954,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f5ba345f6ba3cac959860d5aa5095dcbecd4ad5e6bb8128a371ab7a58af6080a.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "f5e75356fdca6e62786b4cb5f1b432d9f8a129f44667ff1e60960b2f3bde1e79",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "90691c157ef8cd5f343c5502a167db9de1e6b398196f52365d67b7b9158c0eb1",
      "generation_seconds_batch": 24.46615599899087,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.381074905395508,
        "target_z": 1.625000263636156,
        "ce": 6.070269584655762,
        "genuineness": 4.162164688110352,
        "identity": 0.2754846215248108,
        "hypothesis": "De deur staat nog open. Ik heb je Jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f5e75356fdca6e62786b4cb5f1b432d9f8a129f44667ff1e60960b2f3bde1e79.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-1",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-1",
      "key": "f65796835435d5c3166f82b68eddecbfbd5aedcbdeedf3f420f57b0b0b8a481d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "69fb359ae317af3a944ac77aab335f4d95a81eb0d14eefca4c6370046da6911a",
      "generation_seconds_batch": 18.12649925297592,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5719940662384033,
        "target_z": 0.23339841860488147,
        "ce": 6.435632705688477,
        "genuineness": 4.243753433227539,
        "identity": 0.48024824261665344,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f65796835435d5c3166f82b68eddecbfbd5aedcbdeedf3f420f57b0b0b8a481d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "f6ac97da32d60e13693de89f040ee27a8590d0e27b05894a6324cbdf4487a560",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "06eeebd9f37a6298fc97c9350f00c2752516e2db3f4173109cb282159e00d791",
      "generation_seconds_batch": 23.639062172966078,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.081075668334961,
        "target_z": 0.6249999885375584,
        "ce": 6.252951145172119,
        "genuineness": 4.394378662109375,
        "identity": 0.6788065433502197,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f6ac97da32d60e13693de89f040ee27a8590d0e27b05894a6324cbdf4487a560.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "f6b0fffac811c15cc800581fc8bbbef5e76930fc6851990fc33b106a2a6ccadf",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "be32e60a6f02e6a7bbb40bed646d65f6900fb2e0e4c46b1ee701bade8ac2455e",
      "generation_seconds_batch": 23.980190902017057,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.309980869293213,
        "target_z": 1.570312496417987,
        "ce": 5.990842819213867,
        "genuineness": 3.9676074981689453,
        "identity": 0.5357515811920166,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f6b0fffac811c15cc800581fc8bbbef5e76930fc6851990fc33b106a2a6ccadf.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "f7906909b13adfcf2150b0613a036365706937b0f8810310cd6bf8358eedb1c9",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "25a8fddc43b1d44b923dffdd85812fb9afabdc93edcd5f238d2328c9dd58dddc",
      "generation_seconds_batch": 18.119162601069547,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8724830150604248,
        "target_z": -0.3046874691946883,
        "ce": 6.221180438995361,
        "genuineness": 4.362998008728027,
        "identity": 0.47209662199020386,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f7906909b13adfcf2150b0613a036365706937b0f8810310cd6bf8358eedb1c9.mp3"
    },
    {
      "id": "heldout-fr-1",
      "language": "fr",
      "sentences": [
        "Les clés sont sur la table de la cuisine.",
        "J’ai regardé dans le tiroir... puis près de la fenêtre.",
        "Prends-les quand tu partiras."
      ],
      "text": "Les clés sont sur la table de la cuisine. J’ai regardé dans le tiroir... puis près de la fenêtre. Prends-les quand tu partiras.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-1",
      "key": "f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Prends-les quand tu partiras.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f604ac554124523e8cd75be3c859981f2e3e17c897a67a65dc5827a83cdda81e",
      "generation_seconds_batch": 18.174324468011037,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0146703720092773,
        "target_z": -0.19531248495554543,
        "ce": 6.181467056274414,
        "genuineness": 4.331617832183838,
        "identity": 0.5770472288131714,
        "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les, quand tu partiras.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-1",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-1",
      "key": "f804b5872365e0475a76ad7e82aa9dfa9e1c6c5a571661c13aa08c573595571d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] I found the little box.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] It was beside the old window.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We can look inside together.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9817591764cb2b5ab477aefe7356caa5055259b72921870528df19a85e7b98b1",
      "generation_seconds_batch": 24.595551479957066,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.751387596130371,
        "target_z": 1.140624992835974,
        "ce": 6.332377910614014,
        "genuineness": 3.9425034523010254,
        "identity": 0.4068989157676697,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f804b5872365e0475a76ad7e82aa9dfa9e1c6c5a571661c13aa08c573595571d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "f840b12a8454bfdab435d324262ac5b3b0db88f5099c5512309f10f5d3870d04",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "ef7b69cddc1595517420aaf6fc99878797a5fa2d12bff9952a9c711abd6ff626",
      "generation_seconds_batch": 23.222925978014246,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.218574523925781,
        "target_z": 1.4999998624507012,
        "ce": 5.8875885009765625,
        "genuineness": 4.162164688110352,
        "identity": 0.5678042769432068,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f840b12a8454bfdab435d324262ac5b3b0db88f5099c5512309f10f5d3870d04.mp3"
    },
    {
      "id": "heldout-de-2",
      "language": "de",
      "sentences": [
        "Die Straße führt hinter der Brücke nach links.",
        "Geh weiter... bis zu dem kleinen Holztor.",
        "Ich warte auf der anderen Seite."
      ],
      "text": "Die Straße führt hinter der Brücke nach links. Geh weiter... bis zu dem kleinen Holztor. Ich warte auf der anderen Seite.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-2",
      "key": "f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "standard",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich warte auf der anderen Seite.",
      "seed": 1702,
      "scale": 0.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "005069be4f2eb6866a016ecd053e2ae629ecc5eb2040035a36366a3cc2e5466e",
      "generation_seconds_batch": 18.10326093295589,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.2275617122650146,
        "target_z": -0.8007812066576429,
        "ce": 6.356205940246582,
        "genuineness": 4.375550270080566,
        "identity": 0.49925464391708374,
        "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter, bis zum kleinen Holztor. Ich warte auf der anderen Seite.",
        "wer": 0.09523809523809523,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3"
    },
    {
      "id": "heldout-es-1",
      "language": "es",
      "sentences": [
        "Las llaves están en la mesa de la cocina.",
        "Miré en el cajón... y luego junto a la ventana.",
        "Llévatelas cuando te vayas."
      ],
      "text": "Las llaves están en la mesa de la cocina. Miré en el cajón... y luego junto a la ventana. Llévatelas cuando te vayas.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-es-1",
      "key": "f8a5ffba16ba8157d3ccf2d3098a8755e0d0f9d311d0aecc7493f5df4e9b2dce",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "0aa91139851695f5d039234d9ebc04967c34120158cc8da3e14138789f666a1a",
      "generation_seconds_batch": 20.918954427004792,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6545135974884033,
        "target_z": 0.2968750358201299,
        "ce": 6.173524379730225,
        "genuineness": 4.080576419830322,
        "identity": 0.6883895993232727,
        "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f8a5ffba16ba8157d3ccf2d3098a8755e0d0f9d311d0aecc7493f5df4e9b2dce.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-1",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-1",
      "key": "f955de7a6418f7b9e14a5fb2f2a9f0e9dc204cfbc33a09d17fda235cb19379cc",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] He encontrado la cajita.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 4.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "467610a795b3c6eed9490144f566cafaf05c17954e058b769bcd535781faf472",
      "generation_seconds_batch": 24.688469634973444,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.563886642456055,
        "target_z": 1.7656247979744675,
        "ce": 5.959072113037109,
        "genuineness": 3.747946262359619,
        "identity": 0.24767497181892395,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f955de7a6418f7b9e14a5fb2f2a9f0e9dc204cfbc33a09d17fda235cb19379cc.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "f99fd1897ffd4b58f257ed02c6d777798c428b9e9190fd0edf79c7474fd5434c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 129,
      "seconds_generated": 10.32,
      "mp3_sha256": "7b391ecaf3b0ce0f8d6dd099429f7769e0a792fc554178af4b10c94209927d8b",
      "generation_seconds_batch": 23.8706452610204,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.030294418334961,
        "target_z": 0.5859374548666363,
        "ce": 6.046441555023193,
        "genuineness": 4.218649387359619,
        "identity": 0.4655195474624634,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.120000000000001,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f99fd1897ffd4b58f257ed02c6d777798c428b9e9190fd0edf79c7474fd5434c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "f9edb5635209f71c238e32b1ee04f51b39cd0929af2a191c3c6b560747130108",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "49a38d164d5bc59bab1a48205c95d8b73c278863dfd4e989ce4e65dc57087ad5",
      "generation_seconds_batch": 17.706117892055772,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.1521692276000977,
        "target_z": 0.6796873889575973,
        "ce": 6.054384231567383,
        "genuineness": 4.074300289154053,
        "identity": 0.451857328414917,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/f9edb5635209f71c238e32b1ee04f51b39cd0929af2a191c3c6b560747130108.mp3"
    },
    {
      "id": "heldout-fr-2",
      "language": "fr",
      "sentences": [
        "La route tourne à gauche après le pont.",
        "Continue... jusqu’à la petite barrière en bois.",
        "Je t’attendrai de l’autre côté."
      ],
      "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-fr-2",
      "key": "fa2a21b65337769e06876170a7ef7e1eccc8539cd9637387cd3a60609c473f42",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "48788250f9fad7b0945f43a93122f87f6f6941deb0fc0cdc7e41e4c434472d2b",
      "generation_seconds_batch": 20.947430817061104,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6900603771209717,
        "target_z": 0.32421873603014933,
        "ce": 6.1894097328186035,
        "genuineness": 4.507347106933594,
        "identity": 0.8280596137046814,
        "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fa2a21b65337769e06876170a7ef7e1eccc8539cd9637387cd3a60609c473f42.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "fa58447911997cf41e6f7c611de3b4cfd50552a0869cc3b68388efa9e2a84eb8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1701,
      "scale": 0.5,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "86fff9629b8f3c2f7d0ae90dce51e256bf4ef14dc9500d9cdcdb7b8e10ad78f4",
      "generation_seconds_batch": 24.070155836059712,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.289668083190918,
        "target_z": 1.55468726287074,
        "ce": 6.268836498260498,
        "genuineness": 3.7416701316833496,
        "identity": 0.566933274269104,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fa58447911997cf41e6f7c611de3b4cfd50552a0869cc3b68388efa9e2a84eb8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "faa5ddb80a37e63fddc076f6ab6c966159db19fdcb317fa2b4852b0eefd6ff20",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1702,
      "scale": 0.75,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "614127e05b2c8a0032ba5e1af5686aea5199ebec10373494850e658d35872b95",
      "generation_seconds_batch": 23.431594421039335,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.700606346130371,
        "target_z": 1.101562459165052,
        "ce": 5.855817794799805,
        "genuineness": 3.8546390533447266,
        "identity": 0.670341968536377,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/faa5ddb80a37e63fddc076f6ab6c966159db19fdcb317fa2b4852b0eefd6ff20.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-1",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-1",
      "key": "fb26abec7d640045e402cf160c0ea8dd72388ff4f200bf5366fb97796e62fa5d",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Het stond naast het oude raam.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "mp3_sha256": "c672b1f5ab6a0f842eb8dc7135ea6b91bd0b86fd342622862a1f7a4fcb53d882",
      "generation_seconds_batch": 23.05518397805281,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.568575382232666,
        "target_z": 1.0000000916995326,
        "ce": 6.0146708488464355,
        "genuineness": 3.911123275756836,
        "identity": 0.3183411657810211,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fb26abec7d640045e402cf160c0ea8dd72388ff4f200bf5366fb97796e62fa5d.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "fb418b81f4b6d2b20df4047ac59dccebdd5ceca0d83c462c49b02e183ebc5ed8",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "9a72e1ed9dd2025cf1685193c94b6d6e2963895c001c21711ef4b8f867e5e72c",
      "generation_seconds_batch": 24.337650311063044,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2232630252838135,
        "target_z": 0.7343749727767013,
        "ce": 6.0305562019348145,
        "genuineness": 4.030367851257324,
        "identity": 0.40079301595687866,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fb418b81f4b6d2b20df4047ac59dccebdd5ceca0d83c462c49b02e183ebc5ed8.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "fb8286dac5840224752b35b7f33cccb7aa1cb5069aaf57341958b0f7e670097b",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "4dfcdca5ae27a34c060ceb26d45851cba6f46894b97a1c7d8b235f3cf1bbf9d2",
      "generation_seconds_batch": 23.627084046020173,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9896695613861084,
        "target_z": 0.5546875379693377,
        "ce": 6.221180438995361,
        "genuineness": 4.425758361816406,
        "identity": 0.46832433342933655,
        "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise, dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fb8286dac5840224752b35b7f33cccb7aa1cb5069aaf57341958b0f7e670097b.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "fbb90b387cec3045182e78cf1fd83ef6e6957e6c3ea47f2f1db5518d5e8c070e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 0.75,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f8916f4e8cd91370420ff3c2d3bcb182814b17e587bc6a6d05a74310138a6ab5",
      "generation_seconds_batch": 24.06138741201721,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8318580389022827,
        "target_z": -0.33593747779151945,
        "ce": 6.1894097328186035,
        "genuineness": 4.256305694580078,
        "identity": 0.5536019206047058,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fbb90b387cec3045182e78cf1fd83ef6e6957e6c3ea47f2f1db5518d5e8c070e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-en-0",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-en-0",
      "key": "fc2e9f619087c3ace21ebeed5752cb232efc7c5876af1d2508d93bd1b3d0ae93",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] The door is still open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] I put your coat on the chair.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Tell me when you are ready.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d2fde9a6604a6f2e14fa545f6cf55ff4d3fcc3fd29c99d9ebaab21bf080d8639",
      "generation_seconds_batch": 24.804331645020284,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.720918893814087,
        "target_z": 1.1171875093132337,
        "ce": 6.046441555023193,
        "genuineness": 3.340003728866577,
        "identity": 0.5553421974182129,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fc2e9f619087c3ace21ebeed5752cb232efc7c5876af1d2508d93bd1b3d0ae93.mp3"
    },
    {
      "id": "heldout-de-3",
      "language": "de",
      "sentences": [
        "Jemand hat den kleinen blauen Stuhl umgestellt.",
        "Er stand hier... neben dem hohen Bücherregal.",
        "Wir stellen ihn nach dem Essen zurück."
      ],
      "text": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier... neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "heldout-de-3",
      "key": "fc3090240ed86babfd8a2ae6c0118f37e0d13f7614f9ddf506ed66c7e403de1e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "heldout",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 2.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "37fb7fd7c93b9097e180cbfd79760f6fd99ca020d6d09d835f1eeacdc6cf6e7b",
      "generation_seconds_batch": 23.735426774946973,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.009982109069824,
        "target_z": 0.5703125881175195,
        "ce": 6.38003396987915,
        "genuineness": 4.231201171875,
        "identity": 0.39414557814598083,
        "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fc3090240ed86babfd8a2ae6c0118f37e0d13f7614f9ddf506ed66c7e403de1e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "fcc38dca5c7c685ceaad3da7e614eab7a770411eb95d1d720d345003b464c3ea",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "00a58d1856317c4891548ef771fa65997db3e1b0edba39c87a989e17670233a2",
      "generation_seconds_batch": 23.538116502109915,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.730685234069824,
        "target_z": 0.35546865292744795,
        "ce": 6.070269584655762,
        "genuineness": 4.369274139404297,
        "identity": 0.6230802536010742,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fcc38dca5c7c685ceaad3da7e614eab7a770411eb95d1d720d345003b464c3ea.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "fd0598eb5e544e4a820e50600ae1242e86bf6c851275a8ff794552ef4302648e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "d5a2eb3e9e615d78f9a55f01fc5f29d8f6fc0cface503e99d3ea857c879d9c89",
      "generation_seconds_batch": 24.37468330306001,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.3625216484069824,
        "target_z": 0.07226565061139288,
        "ce": 6.173524379730225,
        "genuineness": 4.319066047668457,
        "identity": 0.6085796356201172,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fd0598eb5e544e4a820e50600ae1242e86bf6c851275a8ff794552ef4302648e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-1",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-1",
      "key": "febe9166695cf2921ded2d6e17badacd30f19cfa4ea99ac7fda27f46432e4813",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 2.5,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "691966f5ac87d76b12f9c8563a4ad870a50cbe63b9249a9d56d5de58bcea0273",
      "generation_seconds_batch": 21.052851790911518,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.3045129776000977,
        "target_z": 0.7968749899703637,
        "ce": 6.268836498260498,
        "genuineness": 4.293961524963379,
        "identity": 0.5812730193138123,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/febe9166695cf2921ded2d6e17badacd30f19cfa4ea99ac7fda27f46432e4813.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-es-0",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-es-0",
      "key": "fef1cbd0f850327f7a1a83c23c4649210d75b3d16728e63bd597e90572613d5c",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La puerta sigue abierta.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dime cuándo estás listo.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2820c7d4b867a3df67651f7f15edfcfbd30e3632bc90f133abe1a4f0acd84868",
      "generation_seconds_batch": 24.397478452068754,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.550412178039551,
        "target_z": 0.21679695183417863,
        "ce": 6.117925643920898,
        "genuineness": 3.785602569580078,
        "identity": 0.5523040294647217,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/fef1cbd0f850327f7a1a83c23c4649210d75b3d16728e63bd597e90572613d5c.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-nl-0",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-nl-0",
      "key": "ff52896b2a4c56cf88ea6d14a06ae5b779bd15b516bc6651b535657f4065896e",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] De deur staat nog open.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "seed": 1702,
      "scale": 0.5,
      "cfg": 1.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "f6f246984aca8f1cd97276bb13fbdde2efab890fd4b23936bdfcb7be8164a426",
      "generation_seconds_batch": 23.67621531302575,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2279515266418457,
        "target_z": -0.031249916897298634,
        "ce": 6.086154937744141,
        "genuineness": 4.2249250411987305,
        "identity": 0.6619903445243835,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ff52896b2a4c56cf88ea6d14a06ae5b779bd15b516bc6651b535657f4065896e.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "ffbe927eec7ecc7422ef40fc6c6a8b860b1052395a89f4d4c170e605bb3c9ac4",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 1.0,
      "cfg": 1.25,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "79b60e22db8166d83588d35f021af3a872772d1a585fedd03b89f8f91040efea",
      "generation_seconds_batch": 24.918187833041884,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.085763931274414,
        "target_z": -0.14062508453550657,
        "ce": 6.221180438995361,
        "genuineness": 4.20609712600708,
        "identity": 0.5658565759658813,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ffbe927eec7ecc7422ef40fc6c6a8b860b1052395a89f4d4c170e605bb3c9ac4.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-de-0",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-de-0",
      "key": "ffd83cb7505601c8c67d84337d2c7c4f4cf4eef979be8297090e0c276364e9af",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Die Tür ist noch offen.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "seed": 1701,
      "scale": 0.0,
      "cfg": 3.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "47e3ee5bdaa81b5f48dbe9bb4a5109805d508e4228257a12ea2b0f31c28f8834",
      "generation_seconds_batch": 17.79419536900241,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 3.2486536502838135,
        "target_z": 0.7539062396121623,
        "ce": 6.133810997009277,
        "genuineness": 4.168440818786621,
        "identity": 0.40000462532043457,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ffd83cb7505601c8c67d84337d2c7c4f4cf4eef979be8297090e0c276364e9af.mp3"
    },
    {
      "id": "vn_S_PLAY_reg-fr-0",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "sentence_seconds": [
        3.2,
        3.8,
        3.2
      ],
      "seconds": 10.2,
      "frames": 128,
      "max_frames": 188,
      "reference": true,
      "task_id": "vn_S_PLAY_reg-fr-0",
      "key": "ffe57bd84f175e18a09a193bb1f23100de0ed97b5067bf23ee285b56e9180739",
      "bucket": "vn_S_PLAY_reg",
      "phase": "grid",
      "candidate": "manual-3fb618b13504",
      "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.\nSCRIPT:\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Establish it immediately. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] La porte est encore ouverte.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Sustain the delivery. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Playful speech; light mischief, lively pitch and a smile that remains audible in the words. Preserve the intended style through the end. Begin with the feeling held back, then let it leak through and become unmistakable.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "seed": 1702,
      "scale": 1.0,
      "cfg": 5.0,
      "ended": true,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "mp3_sha256": "2d1ea1b8da104dff442f704b101b018d04c79ddc7d806897fd55180ed7f7c69a",
      "generation_seconds_batch": 22.586942248046398,
      "original_audio_reused": false,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 4.117012023925781,
        "target_z": 1.421874795108857,
        "ce": 6.09409761428833,
        "genuineness": 4.15588903427124,
        "identity": 0.7045215368270874,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/vn_S_PLAY_reg/ffe57bd84f175e18a09a193bb1f23100de0ed97b5067bf23ee285b56e9180739.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "184de6f33020358d0bd86eda0d7854ad61b25667a85802f25772bda155d7c1e3",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.9482650756835938,
        "target_z": -1.0156249584486494,
        "ce": 6.300607204437256,
        "genuineness": 4.356721878051758,
        "identity": 0.5478681325912476,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/26656327802240928855e710.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "cf4f569d07a7804d0380baa67025e0939eb9a42170da120d2a0c2028e07256ac",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4713114500045776,
        "target_z": -0.6132812467761883,
        "ce": 6.316492557525635,
        "genuineness": 4.281409740447998,
        "identity": 0.5640042424201965,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/dce38a55690e295de3e068a9.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "1efb680c27b119466ef8896a45383d7b26995e929542babfc6efe76014e7fdc9",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.5373270511627197,
        "target_z": -0.5624999713438961,
        "ce": 6.09409761428833,
        "genuineness": 4.262581825256348,
        "identity": 0.49904394149780273,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/408a60d0e306d21cea9151ee.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "435c24aacbbfc6a6024bab44ce421d3f9b203cff14ec3764db9197948a17c960",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.212327241897583,
        "target_z": -0.8125000401185455,
        "ce": 6.1894097328186035,
        "genuineness": 4.394378662109375,
        "identity": 0.4469967782497406,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/dad313006c577fbda3b64f4d.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "77764269f80365b2e2f2839926a9bdddbed13a7a8719496fc5bb360304832438",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.197092890739441,
        "target_z": -0.8242187818799156,
        "ce": 6.221180438995361,
        "genuineness": 4.193545341491699,
        "identity": 0.31213831901550293,
        "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/d9049caeddb83dde5f1d864c.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ec3a099e4d5b13d505d7b0ddea7c56020d97d46aa9aca5a4ae10a6e6946189b9",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.8162338733673096,
        "target_z": -1.1171875093132337,
        "ce": 6.070269584655762,
        "genuineness": 4.406930446624756,
        "identity": 0.6035149097442627,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/b4a3460c77b00b008e70ac73.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "c11db9f56cc1a7032bb98a5dab89be1e1c1ea7100e27f9bcc2f3cd66cce7f1ec",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6211159229278564,
        "target_z": -0.49804693750612666,
        "ce": 6.324435234069824,
        "genuineness": 4.093128204345703,
        "identity": 0.4374156594276428,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/dcf1e7a7675da67e335391a3.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-0-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Die Tür ist noch offen.",
        "Ich habe deinen Mantel auf den Stuhl gelegt.",
        "Sag mir, wenn du bereit bist."
      ],
      "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "54edbb1cf3dc613a63d74268f04a57c98076af2892dbbc114f23c20dac2218f4",
      "task_id": "vn_S_PLAY_reg-de-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Die Tür ist noch offen.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Sag mir, wenn du bereit bist.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.0244368314743042,
        "target_z": -0.9570312496417988,
        "ce": 6.109982967376709,
        "genuineness": 4.118232727050781,
        "identity": 0.32186681032180786,
        "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/a7075ee3f9ecbc5cbf917f82.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f1173c8cde6b1eba0cb05f722bb34ddc5813b8468327f7def0eca05a24246c13",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.5017801523208618,
        "target_z": -0.5898437632534481,
        "ce": 6.435632705688477,
        "genuineness": 4.394378662109375,
        "identity": 0.5015671253204346,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/f4da2eecb11a572c7b777206.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "60aaf2d60b9d0978c9c4993f800e121f95dad0bf88d26395c7114f3f806bf967",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.7857651710510254,
        "target_z": -1.140624992835974,
        "ce": 6.3641486167907715,
        "genuineness": 4.137060642242432,
        "identity": 0.4851081371307373,
        "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/677a8f892d45852a53261030.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "7afa085ab52fde77f66b9ca53f304c3ef4ba5ff28c119bceb5d57d9c92965028",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.364670991897583,
        "target_z": -0.6953124391057792,
        "ce": 6.38003396987915,
        "genuineness": 4.281409740447998,
        "identity": 0.736324667930603,
        "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/07ecaab8d7150a0adefcc9e4.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "abb8d7cb5778ccdad98d41943091dda47edbc964f30cae5087a57ee123200e5f",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.3342021703720093,
        "target_z": -0.718750014328052,
        "ce": 6.3641486167907715,
        "genuineness": 3.9676074981689453,
        "identity": 0.592735767364502,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/212379c423382203e6cf4f73.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "1deb8362a78539b1139b90e885ec8542837e5e9b6c625a90763892a0d7ba5de0",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.91779625415802,
        "target_z": -1.039062533670922,
        "ce": 6.395919322967529,
        "genuineness": 4.243753433227539,
        "identity": 0.6998399496078491,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/9cf50b8b821bfec8cb41496b.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "8b80240dee4fb88ecd23c054588d2fa269f662124266bcde4e99a2430ce83c0b",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4560770988464355,
        "target_z": -0.6249999885375584,
        "ce": 6.332377910614014,
        "genuineness": 4.469690799713135,
        "identity": 0.2942480444908142,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/523f1af12225d5c449e80f71.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "9261a6eea90705071a7695e094280cf505163472f02c79a8cab828cf11215aa8",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.9584212303161621,
        "target_z": -1.007812525074091,
        "ce": 6.300607204437256,
        "genuineness": 4.281409740447998,
        "identity": 0.621603786945343,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/b5da8f6d6ae4182b0dad2251.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-de-1-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "de",
      "sentences": [
        "Ich habe die kleine Schachtel gefunden.",
        "Sie stand neben dem alten Fenster.",
        "Wir können gemeinsam hineinschauen."
      ],
      "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "fb59d73ff6d3136c359d6491ccf4951fa9cabd2980eeb4a027b1d2526d081c88",
      "task_id": "vn_S_PLAY_reg-de-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 0.8873275518417358,
        "target_z": -1.0625000171936623,
        "ce": 6.41180419921875,
        "genuineness": 4.218649387359619,
        "identity": 0.6097911596298218,
        "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/de/d00214f4f9a2e46a2b85ed76.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "e33605cc96d9b6197d97888efc76ee936bfb3e6bb05df8bd060105c5fc62a4c5",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4408427476882935,
        "target_z": -0.6367187302989286,
        "ce": 6.133810997009277,
        "genuineness": 3.6663577556610107,
        "identity": 0.3784562051296234,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/1417389af9cd225b8f7c3e7d.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "430f319ab7fb255d57af43bd2bbe88dc13b5bc8576a31fc7f336407ccccc8da4",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.2072491645812988,
        "target_z": -0.8164062568058247,
        "ce": 6.324435234069824,
        "genuineness": 4.193545341491699,
        "identity": 0.33097565174102783,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/9385cce61832a27160dfb4b4.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "e6e9752c170c23ee353dc03782f6447b3431ba15d95568f352f5af86d215de5a",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.826779842376709,
        "target_z": -0.3398437861783312,
        "ce": 6.221180438995361,
        "genuineness": 3.9173994064331055,
        "identity": 0.25364696979522705,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/9d5b06311c17adb1ba2fbaac.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "a47293565aa211ded12a2aa60ad4731721edfa483e55cc0513267c04825d15fd",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.3545145988464355,
        "target_z": -0.7031250558794027,
        "ce": 6.229123115539551,
        "genuineness": 4.093128204345703,
        "identity": 0.24067538976669312,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/c8378e737d1d53ee8452a7e1.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "67fdd30a13b67b38d77192d24ddb5085e1b35ce59bd686433225a6244298d745",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.028635263442993,
        "target_z": -0.18457025151622886,
        "ce": 6.24500846862793,
        "genuineness": 3.986435890197754,
        "identity": 0.2385830283164978,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/2e62d1eb31b1c68e4f22d034.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "15b8bcc8f7fa2b8770f363b159167e2fc599bec24ea81472da34c0bcf96fe496",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6211159229278564,
        "target_z": -0.49804693750612666,
        "ce": 6.141753673553467,
        "genuineness": 3.785602569580078,
        "identity": 0.12073345482349396,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/15ea1b71f24629082430918c.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f2af85c53ba72b6a14d6441259fb12353151ce6b965d38c5f0202832b5c6da1e",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.491623878479004,
        "target_z": -0.597656288327539,
        "ce": 6.157639026641846,
        "genuineness": 4.030367851257324,
        "identity": 0.13748523592948914,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/edf082baa6ca646b6188d1d2.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-0-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "The door is still open.",
        "I put your coat on the chair.",
        "Tell me when you are ready."
      ],
      "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "bde3d4820a012cecbf8c6fdcec46f94aadfa3cbc1992bb811ecffd21cb257c2e",
      "task_id": "vn_S_PLAY_reg-en-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] The door is still open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] I put your coat on the chair.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Tell me when you are ready.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.643967628479004,
        "target_z": -0.48046868731477266,
        "ce": 6.125868320465088,
        "genuineness": 4.036643981933594,
        "identity": 0.3588207960128784,
        "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/a8f40e0cb49aff133b54e214.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "6517fbd23ff25c164c047f97b6ca1c895aef2287649f268225f4ed34e56a69e3",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.05529522895813,
        "target_z": -0.16406256805824682,
        "ce": 6.300607204437256,
        "genuineness": 4.419482707977295,
        "identity": 0.4231838285923004,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/764c5a4e06c723fcded81051.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f7447b7121966b234d41cf7cfdee7f499d890637585b2afc71bf4e1c7caabd68",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.15685772895813,
        "target_z": -0.0859375007164026,
        "ce": 6.403861999511719,
        "genuineness": 4.607763767242432,
        "identity": 0.30272990465164185,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/f8312f751eacc11095ce3c33.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "0c0c77d4f39b25292dc802caa2d0b43450760070e2257ae78f88475a157012d1",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.3849834203720093,
        "target_z": -0.6796874806571298,
        "ce": 6.324435234069824,
        "genuineness": 4.369274139404297,
        "identity": 0.4587814509868622,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/47f19e09847084d5299705a5.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "28cb65e90fc1bcc6681c6388a898ce4627f872586e3205549de73e63283df860",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.460275411605835,
        "target_z": 0.14746091788847887,
        "ce": 6.324435234069824,
        "genuineness": 4.457139015197754,
        "identity": 0.45022231340408325,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/2b1368dd0dd056f8fbd1c4f5.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "11317eaec01569e0bd6db6a7e3a692d1474c7f706c61323df7ab26edafd07491",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0883030891418457,
        "target_z": -0.13867188449233442,
        "ce": 6.332377910614014,
        "genuineness": 4.394378662109375,
        "identity": 0.37208092212677,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/e23611cdb34a22d86e800b82.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "51f1b996bb81f5c92efce7e25405eb4110b13b2946da6ec1d9469cc1cc350e15",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.6595916748046875,
        "target_z": 0.3007812525074091,
        "ce": 6.395919322967529,
        "genuineness": 4.3881025314331055,
        "identity": 0.4677909314632416,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/b8893138202ada8b8c2da8c9.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "bb6a4bc496a22d1214a6d7f7fc399784808540539ba24852f443e18d2b555cbd",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4640841484069824,
        "target_z": 0.15039071795323708,
        "ce": 6.38003396987915,
        "genuineness": 4.331617832183838,
        "identity": 0.44104915857315063,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/d85235f3f3919945227cb68e.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-en-1-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "en",
      "sentences": [
        "I found the little box.",
        "It was beside the old window.",
        "We can look inside together."
      ],
      "text": "I found the little box. It was beside the old window. We can look inside together.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "9bfc1f7bc8108fd573c4f3e5a5e03b56687798b57afdbed6aded405c1f2905b0",
      "task_id": "vn_S_PLAY_reg-en-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] I found the little box.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] It was beside the old window.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.349191665649414,
        "target_z": 0.06201180888240186,
        "ce": 6.252951145172119,
        "genuineness": 4.13078498840332,
        "identity": 0.47704407572746277,
        "hypothesis": "I found the little box. It was beside the old window. We can look inside together.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/en/d44a36bc56b930186be93599.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "0f0386f5428e6c8f71ccbace96b47b273d717413bb54cc8efc2de60f3ec12bd0",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.9439663887023926,
        "target_z": 0.5195312209856948,
        "ce": 6.165581703186035,
        "genuineness": 3.9801597595214844,
        "identity": 0.5579906702041626,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/cbe98fa246bfb8967c0c850a.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "4e1e9109832d06f6d5fb358d8850118670e8345ef52830c2443b0a5169067d38",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6515847444534302,
        "target_z": -0.47460936228385386,
        "ce": 6.0146708488464355,
        "genuineness": 4.262581825256348,
        "identity": 0.64447420835495,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/0b77f9d51cdcff6132ec605d.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ace8fd53daf7d1b10a41b18605e947ce30613eb17c2e23ef18d1a6011fd33628",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4763896465301514,
        "target_z": -0.6093749383893766,
        "ce": 6.054384231567383,
        "genuineness": 3.898571252822876,
        "identity": 0.6767416000366211,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.",
        "wer": 0.06666666666666667,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/a215258bafbc3d98c90acbf8.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "b25771a311e418a5091bbc67db2961401403b197a7895ebeefad131e5e62e2b6",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8572485446929932,
        "target_z": -0.31640630265559094,
        "ce": 5.847874641418457,
        "genuineness": 4.256305694580078,
        "identity": 0.7984673976898193,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/6734c1def86dedf91c2a1c20.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "a6188c0b88ad6dba1c05506282d0f65a5ca2e10431063105829e34edd7622073",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8470923900604248,
        "target_z": -0.32421873603014933,
        "ce": 5.863759994506836,
        "genuineness": 4.042920112609863,
        "identity": 0.7206594347953796,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/37e33c4527a9e0760994159c.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "196d254dbb649c39f26d7419406ec03e72f0aa6ace41ce77fb5514a74b8d3486",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.930881381034851,
        "target_z": -0.2597656104928474,
        "ce": 5.998785495758057,
        "genuineness": 3.911123275756836,
        "identity": 0.4420713782310486,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/ef8a0ba301d46e9ef63622dd.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "04530cb6540e69f9494f3774e943af0651f6b0360d61337a8ba26205fc9073de",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2114474773406982,
        "target_z": -0.04394535037978737,
        "ce": 5.903473377227783,
        "genuineness": 3.9927117824554443,
        "identity": 0.5503692626953125,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/616d4e8fe37251c8fb8d5f24.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-0-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "La puerta sigue abierta.",
        "He dejado tu abrigo sobre la silla.",
        "Dime cuándo estás listo."
      ],
      "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "72d4dd248cf32f79ff13e5d30f3df6b28028a06bd737e2dc598660029352d514",
      "task_id": "vn_S_PLAY_reg-es-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.059983730316162,
        "target_z": -0.9296874577322467,
        "ce": 5.967014789581299,
        "genuineness": 4.306513786315918,
        "identity": 0.6427841782569885,
        "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/14f81f9b406d09a0de0e90d7.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "5e6a19a58c2db45267dc54fa3580f7ca7883519deadb79739ce8070c1c95d9ba",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8166236877441406,
        "target_z": -0.3476562195528896,
        "ce": 6.054384231567383,
        "genuineness": 4.369274139404297,
        "identity": 0.5396909713745117,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/bd380609477fd231d4d19f94.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "15921bbe6e23b679398d763fcdda6f2a41b3d821c809525f9f4300bbe92b82ae",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7252174615859985,
        "target_z": -0.41796876182064285,
        "ce": 6.1894097328186035,
        "genuineness": 4.218649387359619,
        "identity": 0.6483157277107239,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/b5903898fec70e6c27503cac.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "06d1defc8001c5e1b393f70438574b2e94638306896c3b0e93d339cde0f0be5d",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7074440717697144,
        "target_z": -0.43164061192565256,
        "ce": 6.0305562019348145,
        "genuineness": 4.381826400756836,
        "identity": 0.5922259092330933,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/3a93e87741eae258c2857bfe.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "0085ac9a4b65bf6dfc6a943706bdbe083813e4f509f42bb66926545667b29aa5",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.15368390083313,
        "target_z": -0.08837890907083523,
        "ce": 6.157639026641846,
        "genuineness": 4.394378662109375,
        "identity": 0.5633222460746765,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/81b7fe2fb0cc2a9d7c3b3c45.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "59ed7ca95eb7d993343b63aa3da9ae2ee5b40db927bb31e0109c1c3cc6925131",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0844945907592773,
        "target_z": -0.14160150115802755,
        "ce": 6.292664527893066,
        "genuineness": 4.582659721374512,
        "identity": 0.5052546262741089,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/e6ca5a475f18821def52b0dc.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ad6b20cb809f22df6f54dd50a11aff8a9e9efd15a6d1721876c8fb359a7e5f07",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.0184788703918457,
        "target_z": -0.19238286828985232,
        "ce": 6.181467056274414,
        "genuineness": 4.331617832183838,
        "identity": 0.628078043460846,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/39d5516ce72e634a72f22ce1.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "b4f8ea7fc3e8115000a59507fb5965dadc4d0bc5191c9b82b38583b89926e36b",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.303733468055725,
        "target_z": -0.7421874978507922,
        "ce": 6.038498878479004,
        "genuineness": 4.20609712600708,
        "identity": 0.4881269931793213,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/9ea9132f02008946a350ed48.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-es-1-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "es",
      "sentences": [
        "He encontrado la cajita.",
        "Estaba junto a la ventana vieja.",
        "Podemos mirar juntos lo que hay dentro."
      ],
      "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "d3d049b4196468774cdc899d73fa862a53dafc0cf3014ce78735adadb2b2933f",
      "task_id": "vn_S_PLAY_reg-es-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.5707244873046875,
        "target_z": 0.23242181858329541,
        "ce": 6.125868320465088,
        "genuineness": 4.7081804275512695,
        "identity": 0.7254958152770996,
        "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/es/b310d77223f2438ec2a75fef.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "8bb0fde5da4540679e0c4c727e5d9d4db4c95a7c8f03b25122d3fe52abe9cf31",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4357645511627197,
        "target_z": -0.6406250386857403,
        "ce": 6.165581703186035,
        "genuineness": 4.457139015197754,
        "identity": 0.8390992879867554,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/7eab50f60b9fe120162e4d81.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f842788f31aea48d5cf1e71272cc9f1b6cf347414ff1456fc39416fde6755105",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.022287607192993,
        "target_z": -0.1894530682250941,
        "ce": 6.1894097328186035,
        "genuineness": 3.948779582977295,
        "identity": 0.6624451875686646,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/c6b657554ea2872c366aa2b7.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ed2d105012594b2f14777d81c5a067bf570592a5cff88b2691c9507b1c84d42e",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9778540134429932,
        "target_z": -0.22363278518715096,
        "ce": 6.221180438995361,
        "genuineness": 4.6203155517578125,
        "identity": 0.6322094202041626,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/ebe31e990502f6d6d7d614a8.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "2ce9149e10936ea0e8118addc11324d76342f4a1059b7d78b83e448115cc2232",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.875022053718567,
        "target_z": -0.3027343608510487,
        "ce": 6.125868320465088,
        "genuineness": 4.281409740447998,
        "identity": 0.7286936044692993,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/abbad85414c477e43822192b.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "bd343097ef91f28c97e70b5a9120bc3ef670004153c20dadb7e646a0192e2a1e",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.1412335634231567,
        "target_z": -0.867187532238117,
        "ce": 6.1020402908325195,
        "genuineness": 4.507347106933594,
        "identity": 0.7415041923522949,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/7f9621f18673c3b4f6f7ef9b.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "32a70eb605ae3eaa5bd093cb48739dad565b33dc3726b892e604d1fdb8c11fd6",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.2986552715301514,
        "target_z": -0.7460938062376039,
        "ce": 6.117925643920898,
        "genuineness": 4.168440818786621,
        "identity": 0.6720168590545654,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/f713fa038e1bd53e9bc12778.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "e6ddb9de795bc6e89c4052b79d1c756cafd9289aa406ebcf59441e07e521fda9",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.2327122688293457,
        "target_z": -0.027587804365649685,
        "ce": 6.141753673553467,
        "genuineness": 4.469690799713135,
        "identity": 0.6561102867126465,
        "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/03754443d78e8bfc840e7ef8.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-0-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "La porte est encore ouverte.",
        "J’ai posé ton manteau sur la chaise.",
        "Dis-moi quand tu es prêt."
      ],
      "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "faffff9ced501a74bd84a752046d3294bddec24f6b23ab1f1797f40bddf14de2",
      "task_id": "vn_S_PLAY_reg-fr-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La porte est encore ouverte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand tu es prêt.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.263108491897583,
        "target_z": -0.7734375064476234,
        "ce": 5.95112943649292,
        "genuineness": 4.15588903427124,
        "identity": 0.8102350234985352,
        "hypothesis": "La porte est encore ouverte : J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/1264e0c5c04294ee3ffb4494.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 127,
      "seconds_generated": 10.16,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "03d9a464de73a18f480a4b699d3b14b3932300a5f7af9b864bce48cc611e8970",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4357645511627197,
        "target_z": -0.6406250386857403,
        "ce": 6.062326908111572,
        "genuineness": 4.268857479095459,
        "identity": 0.7355878353118896,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.03999999999999915,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/c713719b8a703bf18ac39baf.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ec41a1f569bd472dcdbbf5eae6881c5fae4466ca722cd00f316bdbb672656ebf",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4133028984069824,
        "target_z": 0.11132818428231499,
        "ce": 6.086154937744141,
        "genuineness": 4.607763767242432,
        "identity": 0.8188244104385376,
        "hypothesis": "J'ai trouvé un. La petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.05263157894736842,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/23f1e68b607e613a17139143.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "3cd66319949a33503c9d53069bbd326ab8b5565e705aa3e4fbd1192345814ad6",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.593186378479004,
        "target_z": -0.5195312209856948,
        "ce": 6.149696350097656,
        "genuineness": 4.394378662109375,
        "identity": 0.7755551934242249,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/48d412227ae8aedae6f4c412.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "69b2b2f0dff67505ad3808b53f437eb9daaedacc31707495b6376c1fd89ebe6c",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6287331581115723,
        "target_z": -0.49218752077567535,
        "ce": 6.062326908111572,
        "genuineness": 4.268857479095459,
        "identity": 0.6619312763214111,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/49d5a06241926d72a35fc34f.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "2f05ae3add821daf378e5327f7d62e1c18135cdfd18b7ea53684e4466817acc2",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.4894745349884033,
        "target_z": 0.16992180138963306,
        "ce": 6.149696350097656,
        "genuineness": 4.331617832183838,
        "identity": 0.7397224307060242,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/4419fdba3fcfd5f2cfe82981.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f679242298c94b9225761e551d20b3baa7a577a9455c5e1caa42b74a39715085",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.104806900024414,
        "target_z": -0.12597663440891077,
        "ce": 6.1894097328186035,
        "genuineness": 4.444586753845215,
        "identity": 0.7510710954666138,
        "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/5a3bef0bbb27c8c336b5f996.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "768028b24931121b34af50b301be9cea6fd46ce14c1d3e7134044291d0cb3879",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1117894649505615,
        "target_z": -0.12060542598971993,
        "ce": 6.149696350097656,
        "genuineness": 4.7332844734191895,
        "identity": 0.7759090065956116,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/a140488aa32c01a072769579.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-fr-1-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "fr",
      "sentences": [
        "J’ai trouvé la petite boîte.",
        "Elle était près de la vieille fenêtre.",
        "Nous pouvons regarder ensemble ce qu’elle contient."
      ],
      "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "95e72b4eb13b20cdf7a8267dcd8542136ad9405c8025d134e371d503ee6266d1",
      "task_id": "vn_S_PLAY_reg-fr-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.7176003456115723,
        "target_z": -0.42382808685156165,
        "ce": 6.109982967376709,
        "genuineness": 4.042920112609863,
        "identity": 0.7362415790557861,
        "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/fr/6497772faadce7454113eba7.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "d5b7b2c9abe7441f615b0248910ea2a74be19c3947ea5e4740883f8ba2cf90ad",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.699826955795288,
        "target_z": -0.43749993695657136,
        "ce": 6.09409761428833,
        "genuineness": 3.9927117824554443,
        "identity": 0.6497153043746948,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/c63ee2f324c1615e8fbad697.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "e30008d1c14915fb84e89b80fc5d98021e8be8cad0f33d1d323af00e9dd2a96d",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9207251071929932,
        "target_z": -0.2675781355669383,
        "ce": 6.062326908111572,
        "genuineness": 4.231201171875,
        "identity": 0.7800288200378418,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/8f166a4fda1190c8034eb91f.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f63e81f5f2f61f09be6e61ee64d9fd0be20d52890dc02eee2f4ca1bba2247a3b",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1073460578918457,
        "target_z": -0.12402343436573864,
        "ce": 6.0305562019348145,
        "genuineness": 4.068024158477783,
        "identity": 0.6768790483474731,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/7f917031ae272ac1a655c013.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "adca6d5670d631d165a073c05c18f1624c9a129d2ed38149c7d3297d2554d336",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8090064525604248,
        "target_z": -0.35351563628334093,
        "ce": 5.855817794799805,
        "genuineness": 4.319066047668457,
        "identity": 0.3901821970939636,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/570502f3325ab685fd940d0f.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "a335d5e3b9611f11a41c93a034da7c024cc657a89d1acf721715317fb9472967",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9105689525604248,
        "target_z": -0.2753905689414967,
        "ce": 5.998785495758057,
        "genuineness": 4.005263805389404,
        "identity": 0.6611418128013611,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/bfd28712e14279939ff6f19a.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "1988d8a5a02474d2a12d9786fc1569947d29cb97c683adbcc6d6383800579247",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.1962132453918457,
        "target_z": -0.05566400044162495,
        "ce": 6.09409761428833,
        "genuineness": 4.381826400756836,
        "identity": 0.40680521726608276,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/5014aec51c88728fdaad4988.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "3ba2d5591d111c63ce423e4cd74c5d4dcda6e43b45709bc0e48be704904e7e64",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.9956274032592773,
        "target_z": -0.20996093508214123,
        "ce": 6.022613525390625,
        "genuineness": 4.20609712600708,
        "identity": 0.6818636059761047,
        "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/1cb38a678a2a967bffb6ace6.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-0-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "De deur staat nog open.",
        "Ik heb je jas op de stoel gelegd.",
        "Zeg maar wanneer je klaar bent."
      ],
      "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "ee8b214378ad6fdabd80ca4a7b8607eb42c1fc00e10a6fdebdca725e8062eb45",
      "task_id": "vn_S_PLAY_reg-nl-0",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] De deur staat nog open.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 2.04259991645813,
        "target_z": -0.17382820147597733,
        "ce": 6.141753673553467,
        "genuineness": 4.268857479095459,
        "identity": 0.6361499428749084,
        "hypothesis": "de deur staat nog open ik heb je jas op de stoel gelegd zeg maar wanneer je klaar bent",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/5afdecc1db6e5808ad93bf84.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1701-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "8adf4d6bf6c1e88d3265d43fccc112de04158742273852ba031acf72d55d26d1",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.8420143127441406,
        "target_z": -0.32812495271742853,
        "ce": 6.252951145172119,
        "genuineness": 4.444586753845215,
        "identity": 0.7360107898712158,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/8d3c05f86a27cf242f1cc31b.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1701-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "1c774f3e90c87576e5b77b427008f76c0cd7da4469dfda216eeb5c52fb8ce6cb",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.593186378479004,
        "target_z": -0.5195312209856948,
        "ce": 6.157639026641846,
        "genuineness": 4.061748504638672,
        "identity": 0.682106077671051,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/393be8afbf0b4296b18d6c6c.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1701-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "deea7969ea72e331efb01ce70c57409f7e54a1ec5631740b6511740a422791af",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6947487592697144,
        "target_z": -0.44140624534338313,
        "ce": 6.292664527893066,
        "genuineness": 4.494794845581055,
        "identity": 0.7435531616210938,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/efcaf739f97b5d1f95a454e7.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1701-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1701,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "dca424225f6fca07ad0eb9cfb7ce76333e0520714038c5a40902fed3026b90a4",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.6972877979278564,
        "target_z": -0.43945313699974353,
        "ce": 6.173524379730225,
        "genuineness": 4.306513786315918,
        "identity": 0.7440240383148193,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/181f15f25372eedfe5bece46.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1702-scale0.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "67a4bba56d90db7d0d444ad7e1e46556e3666544f8c179bc86ddcc09d36b9385",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4154521226882935,
        "target_z": -0.6562499971343896,
        "ce": 6.141753673553467,
        "genuineness": 4.080576419830322,
        "identity": 0.5970921516418457,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/88a4138f2c0eb89edcc19451.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1702-scale0.5",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.5,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "b3e0b9477388625939f9aae1132bbb88818aeae4812b20bc705eddfb9b3b090f",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4154521226882935,
        "target_z": -0.6562499971343896,
        "ce": 6.252951145172119,
        "genuineness": 4.406930446624756,
        "identity": 0.7039188146591187,
        "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/3efcd0d194576ed206bbe180.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1702-scale0.75",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 0.75,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "01ac67a7e71cce9068c95d2a29ecf7c29630a26f07324cb535fb6b241bfa36d9",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.4154521226882935,
        "target_z": -0.6562499971343896,
        "ce": 6.213237762451172,
        "genuineness": 4.419482707977295,
        "identity": 0.5625593662261963,
        "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/28527480167c38e9ed60114c.mp3"
    },
    {
      "key": "original-vn_S_PLAY_reg-nl-1-seed1702-scale1.0",
      "bucket": "vn_S_PLAY_reg",
      "language": "nl",
      "sentences": [
        "Ik heb het kleine doosje gevonden.",
        "Het stond naast het oude raam.",
        "We kunnen er samen in kijken."
      ],
      "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.",
      "prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "directions": [
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.",
        "Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word."
      ],
      "seconds": 10.2,
      "frames": 128,
      "seeds": [
        1701,
        1702
      ],
      "scales": [
        0.0,
        0.5,
        0.75,
        1.0
      ],
      "cfg": 1.0,
      "reference": true,
      "case_type": "Neutral wording, target emotion/style varies only through acoustic performance",
      "seed": 1702,
      "scale": 1.0,
      "frames_generated": 128,
      "seconds_generated": 10.24,
      "ended": true,
      "contract_sha256": "02beea177a48576f7419606c87535fb0a2f34db689db0dcd8a7ffa04e1e2d26f",
      "mp3_sha256": "f77cb7380d71f98ab0b2a0f05c7262b5d9d361487a91230e10b6affcd14a6299",
      "task_id": "vn_S_PLAY_reg-nl-1",
      "phase": "standard",
      "candidate": "standard",
      "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.8 seconds duration] Het stond naast het oude raam.\n(Strong Playful Style. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.",
      "original_audio_reused": true,
      "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1",
      "metrics": {
        "valid_waveform": true,
        "target_raw": 1.1209211349487305,
        "target_z": -0.8828124906867663,
        "ce": 6.213237762451172,
        "genuineness": 4.306513786315918,
        "identity": 0.6757011413574219,
        "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.",
        "wer": 0.0,
        "duration_error_s": 0.040000000000000924,
        "model_predictions_not_human_ratings": true
      },
      "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/vn_S_PLAY_reg/nl/ce5d45cc04e4265f66bc710d.mp3"
    }
  ],
  "source_standard_audio_unchanged": true
}