{ "complete": true, "report": { "bucket": "emo_Distress", "label": "Intense Distress", "definition": { "id": "emo_Distress", "category": "emotion", "head": "emo_Distress", "pole": "high", "label": "Intense Distress", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_distress/full-v2-sealed/sealed-selected", "mission": "emotion_distress", "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": 6.128052577972412, "genuineness": 4.152499823570252, "wer": 0.017998817523914853, "identity": 0.5885857537388801, "voiceclap": 0.17045061942189932, "fitness": 0.7579867153345029, "steering_v2": 0.8920206283942064, "raw_target": 2.3356134183704853, "target_cdf": 0.8920206283942064, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 0.99, "by_arm": { "reference": { "n": 50, "ce": 6.1176873970031735, "genuineness": 4.116851906776429, "wer": 0.011723257322951427, "identity": 0.5885857537388801, "fitness": 0.7657623053444611, "steering_v2": 0.9006420454080014 }, "none": { "n": 50, "ce": 6.13841775894165, "genuineness": 4.188147740364075, "wer": 0.024274377724878282, "identity": null, "fitness": 0.7502111253245447, "steering_v2": 0.8833992113804112 } } } } ], "selected_wording": { "id": "manual-e66580c21865", "general": "Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.", "inline": [ "Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.", "Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.", "Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "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": 3.0 }, "n": 20, "target_z": 2.4702147602257423, "target_raw": 2.4780656710267066, "ce": 5.854328322410583, "genuineness": 4.099718332290649, "identity": 0.5425338760018349, "wer": 0.02222222222222222, "valid_fraction": 0.95, "identity_delta": 0.014889516681432725, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 3.137011611839805, "target_raw": 3.0230977326631545, "ce": 5.615849566459656, "genuineness": 3.839576470851898, "identity": 0.4973053548485041, "wer": 0.051456183350533195, "valid_fraction": 0.9, "identity_delta": -0.03033900447189808, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.4702147602257423, "target_raw": 2.4780656710267066, "ce": 5.854328322410583, "genuineness": 4.099718332290649, "identity": 0.5425338760018349, "wer": 0.02222222222222222, "valid_fraction": 0.95, "identity_delta": 0.014889516681432725, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.934081986564629, "target_raw": 2.039836920797825, "ce": 6.018443655967713, "genuineness": 4.248460412025452, "identity": 0.5256794948130846, "wer": 0.013651315789473683, "valid_fraction": 0.95, "identity_delta": -0.001964864507317543, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 0.8643554549847694, "target_raw": 1.1654547825455666, "ce": 6.092310571670533, "genuineness": 4.461218237876892, "identity": 0.5641865476965904, "wer": 0.0335343567251462, "valid_fraction": 0.95, "identity_delta": 0.03654218837618828, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.09667968497910416, "target_raw": 0.5379654556512833, "ce": 6.082580780982971, "genuineness": 4.397830247879028, "identity": 0.5606265097856522, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": 0.032982150465250014, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.07709960759114576, "target_raw": 0.5219609260559082, "ce": 6.1266625881195065, "genuineness": 4.46121826171875, "identity": 0.5480055764317513, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.020361217111349104, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.13405761368922295, "target_raw": 0.3493634469807148, "ce": 6.140959429740906, "genuineness": 4.5286856412887575, "identity": 0.6008918404579162, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.07324748113751411, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 3.070312406684127, "target_raw": 2.9685785710811614, "ce": 5.710863804817199, "genuineness": 3.920851135253906, "identity": 0.47398921251297, "wer": 0.07987207602339182, "valid_fraction": 0.8, "identity_delta": -0.05365514680743218, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.837304618666726, "target_raw": 2.7781206905841827, "ce": 5.817692685127258, "genuineness": 4.033506083488464, "identity": 0.5005014106631279, "wer": 0.11488927588579291, "valid_fraction": 0.8, "identity_delta": -0.027142948657274246, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 3.137011611839805, "target_raw": 3.0230977326631545, "ce": 5.615849566459656, "genuineness": 3.839576470851898, "identity": 0.4973053548485041, "wer": 0.051456183350533195, "valid_fraction": 0.9, "identity_delta": -0.03033900447189808, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.910937426053722, "target_raw": 2.838307298719883, "ce": 5.484745883941651, "genuineness": 3.846480107307434, "identity": 0.48047761954367163, "wer": 0.035469341245270035, "valid_fraction": 0.95, "identity_delta": -0.04716673977673054, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.268359317090608, "target_raw": 2.3130713582038878, "ce": 5.766065263748169, "genuineness": 4.075869357585907, "identity": 0.5179869547486305, "wer": 0.01330409356725146, "valid_fraction": 0.95, "identity_delta": -0.009657404571771621, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 2.136328055639759, "target_raw": 2.205150526762009, "ce": 5.7321104288101195, "genuineness": 4.124822402000428, "identity": 0.5011112090200186, "wer": 0.0285343567251462, "valid_fraction": 0.95, "identity_delta": -0.026533150300383567, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.6471190831037117, "target_raw": 1.8052767507731915, "ce": 5.942194080352783, "genuineness": 4.166872012615204, "identity": 0.5139572873711586, "wer": 0.021800825593395252, "valid_fraction": 1, "identity_delta": -0.013687071949243545, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.5849608994871698, "target_raw": 1.7544693678617478, "ce": 5.838790369033814, "genuineness": 4.187269103527069, "identity": 0.49909072229638696, "wer": 0.014052287581699345, "valid_fraction": 1, "identity_delta": -0.02855363702401519, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.1961913852354136, "target_raw": 1.4366936475038528, "ce": 5.875674223899841, "genuineness": 4.245636260509491, "identity": 0.5679786555469036, "wer": 0.02545687134502924, "valid_fraction": 0.95, "identity_delta": 0.04033429622650146, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.040869127311964, "target_raw": 1.3097350239753722, "ce": 6.055575680732727, "genuineness": 4.357663571834564, "identity": 0.5755214884877204, "wer": 0.015718954248366012, "valid_fraction": 0.95, "identity_delta": 0.047877129167318344, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 0.783593749715153, "target_raw": 1.0994410954415799, "ce": 6.0301590919494625, "genuineness": 4.366763854026795, "identity": 0.5524761810898781, "wer": 0.049392629858961125, "valid_fraction": 0.9, "identity_delta": 0.02483182176947594, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.3233398516046556, "target_raw": 0.7232348635792732, "ce": 6.122691249847412, "genuineness": 4.5042091608047485, "identity": 0.5405959315598011, "wer": 0.008534356725146198, "valid_fraction": 1, "identity_delta": 0.012951572239398957, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.306445298841587, "target_raw": 0.709425450861454, "ce": 6.0516043424606325, "genuineness": 4.364881050586701, "identity": 0.536358741670847, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": 0.008714382350444794, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.2457031064564612, "target_raw": 0.6597754828631878, "ce": 6.055972862243652, "genuineness": 4.392495560646057, "identity": 0.5707935899496078, "wer": 0.013613691090471275, "valid_fraction": 0.95, "identity_delta": 0.043149230629205705, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.11445312331940279, "target_raw": 0.5524932593107224, "ce": 6.100054621696472, "genuineness": 4.459963011741638, "identity": 0.5634219065308571, "wer": 0.010964912280701754, "valid_fraction": 0.95, "identity_delta": 0.03577754721045494, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.06772461328808548, "target_raw": 0.40358327701687813, "ce": 6.123088359832764, "genuineness": 4.472201299667359, "identity": 0.5609530851244926, "wer": 0.029586988304093564, "valid_fraction": 0.95, "identity_delta": 0.0333087258040905, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.06958007647644807, "target_raw": 0.40206664279103277, "ce": 6.094097638130188, "genuineness": 4.41948254108429, "identity": 0.5724839136004448, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": 0.044839554280042646, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.153222655801366, "target_raw": 0.3336981624364853, "ce": 6.111968636512756, "genuineness": 4.42764139175415, "identity": 0.5217544682323932, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.005889891088008881, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.17314452678502348, "target_raw": 0.3174142546951771, "ce": 6.114748597145081, "genuineness": 4.3887299537658695, "identity": 0.5497605130076408, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.022116153687238693, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.2026855510586901, "target_raw": 0.2932677619159222, "ce": 6.115145754814148, "genuineness": 4.416030693054199, "identity": 0.6088804244995117, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": 0.08123606517910957, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 3.4335935974929237, "target_raw": 3.265520429611206, "ce": 5.335522961616516, "genuineness": 3.646274447441101, "identity": 0.4376607097685337, "wer": 0.14825184898520813, "valid_fraction": 0.7, "identity_delta": -0.08998364955186844, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 3.198046786441072, "target_raw": 3.0729871809482576, "ce": 5.643648886680603, "genuineness": 3.829691731929779, "identity": 0.4789700649678707, "wer": 0.10221125730994152, "valid_fraction": 0.8, "identity_delta": -0.048674294352531434, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.917187417394374, "target_raw": 2.843415969610214, "ce": 5.633621335029602, "genuineness": 3.8748791217803955, "identity": 0.4791499162092805, "wer": 0.10280701754385965, "valid_fraction": 0.8, "identity_delta": -0.04849444311112165, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.6763671032849885, "target_raw": 2.64657222032547, "ce": 5.677107453346252, "genuineness": 3.947053647041321, "identity": 0.47988521233201026, "wer": 0.1053764619883041, "valid_fraction": 0.8, "identity_delta": -0.04775914698839188, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.9564452769653384, "target_raw": 2.058116416633129, "ce": 5.803991603851318, "genuineness": 4.073045158386231, "identity": 0.49315090700984, "wer": 0.07968137254901961, "valid_fraction": 0.85, "identity_delta": -0.03449345231056213, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.805371083887173, "target_raw": 1.934630112349987, "ce": 5.913997530937195, "genuineness": 4.113211810588837, "identity": 0.544716963171959, "wer": 0.07923976608187135, "valid_fraction": 0.85, "identity_delta": 0.01707260385155678, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.3554687494872754, "target_raw": 0.16838453635573386, "ce": 6.1878211975097654, "genuineness": 4.366449975967408, "identity": 0.5276443593204021, "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": -0.363916011284644, "target_raw": 0.16147984191775322, "ce": 6.155256199836731, "genuineness": 4.329892075061798, "identity": 0.5755264952778816, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.04788213595747948, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.33837890836498885, "target_raw": 0.182353575527668, "ce": 6.202912282943726, "genuineness": 4.340404391288757, "identity": 0.5542977839708328, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": 0.02665342465043068, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.3224609405051357, "target_raw": 0.19536473900079726, "ce": 6.168560194969177, "genuineness": 4.327224791049957, "identity": 0.5762839019298553, "wer": 0.04643962848297213, "valid_fraction": 0.95, "identity_delta": 0.048639542609453204, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.3534374991568529, "target_raw": 0.17004485696554184, "ce": 6.2369068908691405, "genuineness": 4.357977328300476, "identity": 0.579327247440815, "wer": 0.013068699416525503, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.9219335489991143, "target_raw": 2.02990692794323, "ce": 5.950255851745606, "genuineness": 4.088798027038575, "identity": 0.5325792555510998, "wer": 0.030243459439111612, "valid_fraction": 0.94, "identity_delta": -0.04674799188971519, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 3.2826561484691403, "target_raw": 3.1421458983421324, "ce": 5.654858016967774, "genuineness": 3.7308126735687255, "identity": 0.4607018177956343, "wer": 0.09337093722448413, "valid_fraction": 0.84, "identity_delta": -0.1186254296451807, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 3.2185936605694403, "target_raw": 3.0897819590568543, "ce": 5.7452356719970705, "genuineness": 3.8324217557907105, "identity": 0.47871300172060727, "wer": 0.08065979672501411, "valid_fraction": 0.84, "identity_delta": -0.10061424572020769, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.06406248789970001, "ci95_z": [ -0.1278124896315697, 0.2674999611696588 ], "language_deltas": { "en": 0.026562447246338095, "de": -0.2609375007975715, "fr": 0.07812504215735391, "nl": 0.4109374388148674, "es": 0.06562501207751219 }, "languages_improved": 4, "clear_gain": false, "delta_ce": -0.09037765502929687, "delta_genuineness": -0.10160908222198486, "delta_wer": 0.01271114049947002, "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": 1.360722599470026, "ci95_z": [ 1.1048241991852847, 1.6404295984767714 ], "language_deltas": { "en": 1.8048826692931776, "de": 1.2388671333648302, "fr": 1.2652343533231443, "nl": 1.5993163307726699, "es": 0.8953125105963078 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.29539783477783205, "delta_genuineness": -0.3579853534698486, "delta_wer": 0.06312747778537252, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 2.275371048155967, "ci95_z": [ 1.791289025130924, 2.890156188393294 ], "language_deltas": { "en": 1.523632798271893, "de": 2.076757749278211, "fr": 2.3743163690561047, "nl": 1.9697265097036112, "es": 3.4324218144700156 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.2866510391235352, "delta_genuineness": -0.26917930126190187, "delta_wer": 0.017174760022586107, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 3.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793024413.3169897, "example": { "text": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier... naast de hoge boekenkast. We zetten het na de lunch terug.", "sentences": [ "Iemand heeft het kleine blauwe stoeltje verplaatst.", "Het stond hier... naast de hoge boekenkast.", "We zetten het na de lunch terug." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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.", "language": "nl", "seed": 1702, "scale": 0.0, "cfg": 3.0, "frames": 128, "reference": true } }, "rows": [ { "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": "006805b1c56057b13c0ec0cef8714a4c74e2e595c0b4a30295074feead717ef5", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b2935e3b8337f7ae3f2943002584f5d0a6d79544fd67b3b372e18739da65e4f", "generation_seconds_batch": 19.130469389958307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.295486569404602, "target_z": 1.0234374470184606, "ce": 6.038498878479004, "genuineness": 3.9173994064331055, "identity": 0.47953927516937256, "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/emo_Distress/006805b1c56057b13c0ec0cef8714a4c74e2e595c0b4a30295074feead717ef5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "007e035b5c25f9f95002c911f31350ddba3e3a536f9242191b401473303264a1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0ee80ef48855cf6622c377d5802f2e97842e09d0b89f1e72f9e28acc521ec739", "generation_seconds_batch": 22.511927800020203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8255119323730469, "target_z": 1.671874976072853, "ce": 5.073464393615723, "genuineness": 3.6475296020507812, "identity": 0.3821980357170105, "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/emo_Distress/007e035b5c25f9f95002c911f31350ddba3e3a536f9242191b401473303264a1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "00975ca8b6ea764a00034746dcb8db938afc7afdc0717c8310abad748374cd9a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ffb3f3e023ddd736fed93afbc0897dc13d68dd2a5cd73042031d1b264551edfa", "generation_seconds_batch": 21.03209709993098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.754037857055664, "target_z": 4.031249965818362, "ce": 5.383228778839111, "genuineness": 3.478076457977295, "identity": 0.5742102861404419, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Mira, Pipote, mira, Fan. Si está, no respiro aquí. Dime cuándo estás listo.", "wer": 0.8666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/00975ca8b6ea764a00034746dcb8db938afc7afdc0717c8310abad748374cd9a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "009a7fe97957bed5b962d8efb6bffaabcdd6520d7666905873e1514c1a4b6f7d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f9619059a524a749acf51e7191e87c4f1a9ef8498a86ffeb9a5cd4ee6c0665be", "generation_seconds_batch": 21.003098550019786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16678807139396667, "target_z": -0.35742187827574035, "ce": 6.308549880981445, "genuineness": 4.68307638168335, "identity": 0.680575966835022, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/009a7fe97957bed5b962d8efb6bffaabcdd6520d7666905873e1514c1a4b6f7d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "009b2569818e571fb2da38c9c9bf061a3300791c2006710485cf4094c96bd547", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ec6a55193cdb018a8eab12ba80965cf94ae578e49e27388e85210ca0ca9f8c29", "generation_seconds_batch": 15.956516021047719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.042630672454834, "target_z": 1.9374998860612056, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.45122283697128296, "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/emo_Distress/009b2569818e571fb2da38c9c9bf061a3300791c2006710485cf4094c96bd547.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "014cb4e58be3fb8f7de628cba937f38aefa987d9b1dd6be3b881f0e92b7a5421", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dfde0d6d7b76b46ae126c069b81dfed7a2e021ced59f373554c756aa826dcbbf", "generation_seconds_batch": 21.801215845975094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.921299695968628, "target_z": 1.7890625393088841, "ce": 6.038498878479004, "genuineness": 3.9425034523010254, "identity": 0.5269033312797546, "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/emo_Distress/014cb4e58be3fb8f7de628cba937f38aefa987d9b1dd6be3b881f0e92b7a5421.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "01aceb55190e5c8e4c83fb9e038db53b1bf27b7626447bd2af7d52061f564c7b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "39b5da955c2a399379414d03bd8359a2f2ab5a444d16720f7cb056870754ae8b", "generation_seconds_batch": 16.36108341498766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4461688995361328, "target_z": -0.015625001139387945, "ce": 6.062326908111572, "genuineness": 4.846253395080566, "identity": 0.8332502245903015, "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/emo_Distress/01aceb55190e5c8e4c83fb9e038db53b1bf27b7626447bd2af7d52061f564c7b.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "36facf87ba8d43aaa36faccd0bd717a78c8e58908c4f4ee325dab55db524610c", "generation_seconds_batch": 15.539491947973147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07898268103599548, "target_z": -0.46484373832127357, "ce": 5.9431867599487305, "genuineness": 4.557555198669434, "identity": 0.6670975089073181, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-les 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/emo_Distress/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "01fe6a6a5f6a34e9afd3303332652e8cad0760eba809df3d02561111e47e41ef", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "c545e7417ef7a379f8f9975a116bdd78d437e1758a728008c0e37217ac945bcf", "generation_seconds_batch": 22.0371443569893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.838283658027649, "target_z": 1.6875000136726552, "ce": 6.070269584655762, "genuineness": 4.18099308013916, "identity": 0.31855154037475586, "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/emo_Distress/01fe6a6a5f6a34e9afd3303332652e8cad0760eba809df3d02561111e47e41ef.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "027fc15afcc295614a609d2fc27855818390f0cbd4793db56981f6488fb3d42a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9d8468f85be9834fbdc360296076ee8b91b2c3e99dbadf1fa1ec9e4610c95d0d", "generation_seconds_batch": 23.60450974199921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44457244873046875, "target_z": -0.0175781126091561, "ce": 5.863759994506836, "genuineness": 4.582659721374512, "identity": 0.6763886213302612, "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/emo_Distress/027fc15afcc295614a609d2fc27855818390f0cbd4793db56981f6488fb3d42a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "032739feef690a9c7078d3a6ee7df7c6f77eea5064c63a78aa144df868532beb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ff8c26146a3a308fe97d9b6c2b4cd7940b2e25eb56517e1a0c086d08cd0dfd79", "generation_seconds_batch": 19.85605293698609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8127403259277344, "target_z": 1.6562500843147079, "ce": 5.661221981048584, "genuineness": 4.356721878051758, "identity": 0.4645202159881592, "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/emo_Distress/032739feef690a9c7078d3a6ee7df7c6f77eea5064c63a78aa144df868532beb.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": "03a0117fcfe997d91d3c8a2252f94bb135be28e01514c6e98eae0beb5d5dfbe0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6694629ca3e30a0d303e0e5003a08a5004010e292165ffab8f9b70023de0ac67", "generation_seconds_batch": 22.525880674947985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3198001384735107, "target_z": 3.499999854158343, "ce": 5.71682071685791, "genuineness": 3.7667744159698486, "identity": 0.27071624994277954, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het trekje en legde mijn telefoon weg. Zeg maar van niet meer kunnen praten.", "wer": 0.21739130434782608, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/03a0117fcfe997d91d3c8a2252f94bb135be28e01514c6e98eae0beb5d5dfbe0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "03aa72006fd1e1155bdd67f2feb05c09e64e38c8dcb7470424029752144a02f9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "614d26ae29f172612e475c5f6b9e5f3e30639ee2ffc0142ca24a5946a367c015", "generation_seconds_batch": 23.0926042990759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1741554737091064, "target_z": 0.8749999544244822, "ce": 6.181467056274414, "genuineness": 4.055472373962402, "identity": 0.4370827078819275, "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": 0.03999999999999915, "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/emo_Distress/03aa72006fd1e1155bdd67f2feb05c09e64e38c8dcb7470424029752144a02f9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "04a6c8ba20dedf0ce9e5ee0fdb5deb6e5e801f812dec1399c23eac730dfdb30b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a5ba2bee91bc49a527fab6a6a3e019f4e23174d4540d95e3b65acecd281547da", "generation_seconds_batch": 20.715315215988085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7734435796737671, "target_z": 0.3847656211545657, "ce": 5.871703147888184, "genuineness": 3.8420867919921875, "identity": 0.5062718391418457, "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/emo_Distress/04a6c8ba20dedf0ce9e5ee0fdb5deb6e5e801f812dec1399c23eac730dfdb30b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "04fd1ae532fc9a76affa7b76f7731cc9433507ffcfcaa9c8c11b69ad67068820", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f1ee507ca0359a1c48b682a1895d472b7b40c044af874462750f491a54fffde0", "generation_seconds_batch": 22.56506997696124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0240881443023682, "target_z": 0.6914063095330201, "ce": 5.982900142669678, "genuineness": 4.394378662109375, "identity": 0.5238947868347168, "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/emo_Distress/04fd1ae532fc9a76affa7b76f7731cc9433507ffcfcaa9c8c11b69ad67068820.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "45a60c53f4c219fd83896b2f9d4122c5caef5e8c8e7900a96991a5d3154a638d", "generation_seconds_batch": 16.88169759698212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21947132050991058, "target_z": -0.29296874401821327, "ce": 6.372091293334961, "genuineness": 4.570107460021973, "identity": 0.5384782552719116, "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/emo_Distress/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "05b53bb0a54b6aa4b6bbf15b603d14a9d89ee98ac8731dbbaca49d10f857776b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "38dacbab400c1819ef807fa394fee972b0112a3925b10b0f0e2d85a75a21fe36", "generation_seconds_batch": 22.569465843960643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.6334228515625, "genuineness": 3.8169827461242676, "identity": 0.41188549995422363, "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/emo_Distress/05b53bb0a54b6aa4b6bbf15b603d14a9d89ee98ac8731dbbaca49d10f857776b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "05c77d4090b12dcf149618e51bcf17ba5b0a8b7a3a6b196dcaf60421baffa907", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "19f995943d1a9419eb30ba9d7551abf6912023bb0e4e549e77142681bd96124f", "generation_seconds_batch": 24.13925038801972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9602296352386475, "target_z": 0.6132812673756661, "ce": 5.847874641418457, "genuineness": 4.645420074462891, "identity": 0.6267130374908447, "hypothesis": "He encontrado la cajita. Estaba junto a la. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.23529411764705882, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/05c77d4090b12dcf149618e51bcf17ba5b0a8b7a3a6b196dcaf60421baffa907.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "05ddfc707ffa10e0a5450b82c74d8edb1929ccc5ae8d6d70c2dc6a0294a68031", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a167b16aaca71a8a695e76ba4aeba0ec31b228196c31feed08dc0c79c98b8e30", "generation_seconds_batch": 23.053550151991658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6249726414680481, "target_z": 0.2031250148120433, "ce": 6.141753673553467, "genuineness": 4.494794845581055, "identity": 0.5807459354400635, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken hè.", "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/emo_Distress/05ddfc707ffa10e0a5450b82c74d8edb1929ccc5ae8d6d70c2dc6a0294a68031.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "06044517df89225fd3b54f9ff69d3a91304ca3cb83523d78036e1a500718fe25", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "79620b46afc3861bdc8d425f32b48edfde7144b8fc59a2e90a4735f3298955b8", "generation_seconds_batch": 21.70558037504088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.695216953754425, "target_z": 0.28906250284846985, "ce": 5.816103935241699, "genuineness": 3.9550557136535645, "identity": 0.5753600001335144, "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/emo_Distress/06044517df89225fd3b54f9ff69d3a91304ca3cb83523d78036e1a500718fe25.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": "0655f096662a812877e0c7ff4eb652b90f83b691f643b008715b1215cacd6ae9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d965cd7325f74a305828e114e7139566c2ad12c9d5b22a2802bd56b9aac6cb5", "generation_seconds_batch": 16.97468567197211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4934478998184204, "target_z": 1.265625019369595, "ce": 6.141753673553467, "genuineness": 4.218649387359619, "identity": 0.539055347442627, "hypothesis": "Road turns left behind the bridge. Keep going. Until you sh reach the small wooden gate. I will meet you on the other side.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/0655f096662a812877e0c7ff4eb652b90f83b691f643b008715b1215cacd6ae9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "06bcae7273e00d11b0af6de52e9fdc3c1ae060fa8a328b6208135dc9dec0f813", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ffa7a17aab3a7fb5a4105796b110f70b30fba4b7d31e07275416a1889f1fd385", "generation_seconds_batch": 15.90213342802599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2857244610786438, "target_z": -0.21191408934682845, "ce": 6.006728172302246, "genuineness": 4.406930446624756, "identity": 0.5365891456604004, "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/emo_Distress/06bcae7273e00d11b0af6de52e9fdc3c1ae060fa8a328b6208135dc9dec0f813.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "07293974e1cd0da5ad9ae15dcf5a051b8bbe9c4925e4d7d1678259aa8178a0ce", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f1c77c75b6da9e41395f41048ca57d3ce43e95f5eee91a270a31420265a5bfe9", "generation_seconds_batch": 21.35383791301865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.285292863845825, "target_z": 2.234374871249162, "ce": 5.935244083404541, "genuineness": 4.143336772918701, "identity": 0.6062216758728027, "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/emo_Distress/07293974e1cd0da5ad9ae15dcf5a051b8bbe9c4925e4d7d1678259aa8178a0ce.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "075d96da81476f917c2b6d976fa314b959ca1ac976142f272addf336a606639e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "e3c3cf1f9d01db6c633eee8a30095c5e9042bc3620a513d3f5c9f2493c165b19", "generation_seconds_batch": 21.68031800398603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4768683910369873, "target_z": 2.468749997721224, "ce": 5.589737892150879, "genuineness": 3.7918784618377686, "identity": 0.8429164886474609, "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/emo_Distress/075d96da81476f917c2b6d976fa314b959ca1ac976142f272addf336a606639e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "07c4f950410e47617d50cad2208cbf4776408c92198a35f9309845abed263be6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5713baca3ddff1a6e11e0c1c71e595846596952116e018cff0a2ea58415669c9", "generation_seconds_batch": 21.208039171993732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2176265716552734, "target_z": 3.3749998450432397, "ce": 5.478540420532227, "genuineness": 3.9048471450805664, "identity": 0.7472410798072815, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête. Recustus, chez vous. Dis-moi quand tu es prêt.", "wer": 0.5, "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/emo_Distress/07c4f950410e47617d50cad2208cbf4776408c92198a35f9309845abed263be6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "087cf0e2e17f630b611f3ba688596ce4a0647f18781c4fdc175e0ed3af7f6244", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ba460bc213304198be9837e78ddc311af979817d636e2b8ec0d29d9f5145ad04", "generation_seconds_batch": 22.93178117100615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14922699332237244, "target_z": -0.378906250284847, "ce": 6.308549880981445, "genuineness": 4.3127899169921875, "identity": 0.546647846698761, "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/emo_Distress/087cf0e2e17f630b611f3ba688596ce4a0647f18781c4fdc175e0ed3af7f6244.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "088a6b7cb198660b4c94218aa3f76d7f65071095b3878a29b58ea8fdbf162ca9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "967df451158ae6cd18d80a454ad3acadc46c932e750bebdf8161290561e51b16", "generation_seconds_batch": 25.23160865297541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12528005242347717, "target_z": -0.40820314109385475, "ce": 6.165581703186035, "genuineness": 4.469690799713135, "identity": 0.7319000959396362, "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/emo_Distress/088a6b7cb198660b4c94218aa3f76d7f65071095b3878a29b58ea8fdbf162ca9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "088df15c2388c81a7de993ad4a1821b616981653b7d451158f200dce815b46ff", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6444ef9f68b69bc833f18d4725c30646b30f5dd0be4b5abc83765c1f36fccc55", "generation_seconds_batch": 21.818212548969314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5700781345367432, "target_z": 1.3593750991267513, "ce": 5.605623245239258, "genuineness": 3.7667744159698486, "identity": 0.43782249093055725, "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/emo_Distress/088df15c2388c81a7de993ad4a1821b616981653b7d451158f200dce815b46ff.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": "08c557f28130fc34a335f214cc8b5eb6672cc47bc60e854888d55b39f007af34", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ec6023dd2171b9d480975600692d3445f1c8485bc97c3ef1db7d81232dd84304", "generation_seconds_batch": 18.6053647340741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3274158239364624, "target_z": 1.0624999680971376, "ce": 6.070269584655762, "genuineness": 4.030367851257324, "identity": 0.4422207772731781, "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/emo_Distress/08c557f28130fc34a335f214cc8b5eb6672cc47bc60e854888d55b39f007af34.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": "08e4d6ccdf71ed97fe92ff905277d7704d12da669b517a65edfb92872177bef6", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e39bb3637f0a35f6c3ebef1261fe69481cb18c212c321e246fdd8a75a47cc905", "generation_seconds_batch": 15.800462553044781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1282248497009277, "target_z": 3.2656250193695953, "ce": 5.816103935241699, "genuineness": 3.7416701316833496, "identity": -0.07371945679187775, "hypothesis": "De weg. De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "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/emo_Distress/08e4d6ccdf71ed97fe92ff905277d7704d12da669b517a65edfb92872177bef6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "08fd9b4815a38a2e115e4f8f1d53c854c23c171e33895f65bfad6b72fb47fe46", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0c9c8b20ab161d50c859be6a340b628ea062b9557fb07527baa909edde8c8164", "generation_seconds_batch": 21.670634682988748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1843491494655609, "target_z": -0.3359375062666337, "ce": 5.998785495758057, "genuineness": 4.582659721374512, "identity": 0.7352651357650757, "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/emo_Distress/08fd9b4815a38a2e115e4f8f1d53c854c23c171e33895f65bfad6b72fb47fe46.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "090c6738789b73dbc95945e46d32a80eafb8faef7cec8255ad6eeadaabe4de88", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cd72554a07faba2e8c86b1b9aefc592a84f86e46c993eb14bd132054185481c7", "generation_seconds_batch": 16.298488704953343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1396482288837433, "target_z": -0.3906249920242844, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.4992554187774658, "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/emo_Distress/090c6738789b73dbc95945e46d32a80eafb8faef7cec8255ad6eeadaabe4de88.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "097e5053e4362f1edc7f52dc65c968b8cc6b7a04f64c8eb61c5373ba506715be", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1563559e47e4c27700da944c8c0402c4bbaf7f15168e3a4127794b9044b1225a", "generation_seconds_batch": 21.778745813993737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23224301636219025, "target_z": -0.27734374287882535, "ce": 6.2767791748046875, "genuineness": 4.218649387359619, "identity": 0.3509136438369751, "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/emo_Distress/097e5053e4362f1edc7f52dc65c968b8cc6b7a04f64c8eb61c5373ba506715be.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "09c4e60559107e183a7fef33d99d907472b66ceec7ed5631679d790c9da973e3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "632dae009cca080c3cd9ad6a8344b40a7de1891d412cc5927ba7f0b854b4644c", "generation_seconds_batch": 22.076806891011074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4385533332824707, "target_z": 2.4218750307634744, "ce": 5.831989288330078, "genuineness": 4.444586753845215, "identity": 0.44046252965927124, "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/emo_Distress/09c4e60559107e183a7fef33d99d907472b66ceec7ed5631679d790c9da973e3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "09d4dcdf7a0edc3247a55ce30623b216913d4cccbb0b65a34fbc40249c604259", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "cef5856c0d1f030e4c6be75fa2e881b815720aec2971d66e45f90379c1874386", "generation_seconds_batch": 22.185328477993608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3982750475406647, "target_z": -0.07421874629698919, "ce": 6.006728172302246, "genuineness": 4.394378662109375, "identity": 0.48389580845832825, "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/emo_Distress/09d4dcdf7a0edc3247a55ce30623b216913d4cccbb0b65a34fbc40249c604259.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": "09ee50aa54ec706c1f0120e9156b90b9fac36ac923e16c026579daa658fa331c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b0a64f108af341059d5267c349322ab8e18a44c7fd6e24e7ea5df4f182261ca", "generation_seconds_batch": 23.60451910609845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5496907234191895, "target_z": 3.7812499475881545, "ce": 5.629451274871826, "genuineness": 3.7667744159698486, "identity": 0.5871545076370239, "hypothesis": "La route tourne à gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté. C'est là aussi ! Je t'attendrai de l'autre côté !", "wer": 0.4, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/09ee50aa54ec706c1f0120e9156b90b9fac36ac923e16c026579daa658fa331c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "0a788fd01efe6029374cfd92748ef1f3091416b34f39a2cd0ba9b541233beabc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f707551f3ce142590eb4c666b94893def69cf6657c39e9e3ea1b291fbb672e12", "generation_seconds_batch": 23.413634181022644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.544534683227539, "target_z": 1.328125023927147, "ce": 5.287916660308838, "genuineness": 4.143336772918701, "identity": 0.43110209703445435, "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/emo_Distress/0a788fd01efe6029374cfd92748ef1f3091416b34f39a2cd0ba9b541233beabc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "0b0e38d527120b2b3e9a9840956e99c05993349a39c66efd56c60f7e8b81672f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b23a8cb305b36ea5dad92789361f6842bfe009b41589b2881b565189212beb6a", "generation_seconds_batch": 21.519763472955674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.702950954437256, "target_z": 3.968749815419153, "ce": 5.289902210235596, "genuineness": 3.8671910762786865, "identity": 0.6147723197937012, "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/emo_Distress/0b0e38d527120b2b3e9a9840956e99c05993349a39c66efd56c60f7e8b81672f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "0b33391d75915e3dc895d3af17b1f16f51dd25687941227a945c4630b877cb71", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "63810f9e8ff16a1484404e27e737e040974e8f5ac73ac518771fd2dee733a7af", "generation_seconds_batch": 17.136157016037032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.604218602180481, "target_z": 0.17773434694257187, "ce": 6.348263263702393, "genuineness": 4.758388519287109, "identity": 0.44775015115737915, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/0b33391d75915e3dc895d3af17b1f16f51dd25687941227a945c4630b877cb71.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "0c0fa2600d8a13f173381756dfd4d1e5b6ba75612256e6c04bf96032243ffe60", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "95d075285330b4a7d47cd8bdce86407ce344da8a67809bba940696ecb718eb7f", "generation_seconds_batch": 22.865615687100217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13805174827575684, "target_z": -0.3925781399544668, "ce": 5.879645347595215, "genuineness": 4.645420074462891, "identity": 0.6588125228881836, "hypothesis": "J'y ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/0c0fa2600d8a13f173381756dfd4d1e5b6ba75612256e6c04bf96032243ffe60.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "0c48e829370d91fb73dacc9deb683c2504a3764e2bf8da44916f3eb7c85f2225", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "240bfe108bafec9ccea2845eb9a2d35ad25a9e9b35a4ff44f7590ff9603e2a63", "generation_seconds_batch": 15.90213342802599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2418217808008194, "target_z": -0.2656250011393879, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.4734184741973877, "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/emo_Distress/0c48e829370d91fb73dacc9deb683c2504a3764e2bf8da44916f3eb7c85f2225.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "a583d418f54211b08786d0b6394850fec94ccdcb57bf59ec9d8bee22e44f07b5", "generation_seconds_batch": 17.474692296003923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09973669052124023, "target_z": -0.4394531069122164, "ce": 6.062326908111572, "genuineness": 4.243753433227539, "identity": 0.6592550277709961, "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/emo_Distress/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "0cfda500a2475d90f120ecaf600d2e38c203ae277ff3a427530f783348974d1b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "e4bb568b80e566bcc3f88a92b82b004fd65a1ca2d296dbb0c1c6ac8ea3e5f9e4", "generation_seconds_batch": 21.415206364006735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 5.283945083618164, "genuineness": 4.218649387359619, "identity": 0.631572425365448, "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/emo_Distress/0cfda500a2475d90f120ecaf600d2e38c203ae277ff3a427530f783348974d1b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "0d18c9f3e8d3863b7169ea88b98b8f10199aa6b2e72b83f2402b0dd234f53c72", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "72639114fda2dffc5d55076b267bdba49d0f8bab9348f9579294ddaf761d40b8", "generation_seconds_batch": 22.024435746949166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0005078315734863, "target_z": 3.109374935054887, "ce": 5.7684478759765625, "genuineness": 3.9048471450805664, "identity": 0.48088741302490234, "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/emo_Distress/0d18c9f3e8d3863b7169ea88b98b8f10199aa6b2e72b83f2402b0dd234f53c72.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "0d209fde94b4e3f5b2b489028a163f6fb7f246e9895d1b4ca0f8aa5077767f11", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a6bd640c4d6a18c074a471dd1d7ea34ea06513e880e37585cf329a9f3388dda8", "generation_seconds_batch": 15.995918376953341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.617357015609741, "target_z": 2.6406249737940772, "ce": 5.673136234283447, "genuineness": 4.256305694580078, "identity": 0.5356106162071228, "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/emo_Distress/0d209fde94b4e3f5b2b489028a163f6fb7f246e9895d1b4ca0f8aa5077767f11.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "0d577a6bbf20a570ae4fe08b47b5cee3ed369e54b73058a269386d5f371a94cb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9814e550bcfef59ea90981840f44a32c9e35832927df0cb2eec69ae9978b184a", "generation_seconds_batch": 17.425187162007205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013279438018799, "target_z": 3.1249998268130326, "ce": 5.788304805755615, "genuineness": 4.250029563903809, "identity": 0.7545464634895325, "hypothesis": "j'ai trouvé la petite boîte. Elle était... Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/0d577a6bbf20a570ae4fe08b47b5cee3ed369e54b73058a269386d5f371a94cb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "0d9c96b66160929012fb45f2c01ff7eb2c1649b031b652c9e78b8a19425a08be", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "853cdd8d163128631587f08c605167f595506a1aa9ec7b6b6f72af49b9b13183", "generation_seconds_batch": 21.04007206298411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1262617111206055, "target_z": 0.8164063186481236, "ce": 5.990842819213867, "genuineness": 4.494794845581055, "identity": 0.665958046913147, "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/emo_Distress/0d9c96b66160929012fb45f2c01ff7eb2c1649b031b652c9e78b8a19425a08be.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": "0e2b0e8c4f0f4c6326124a318c279388a9c8b6c83b8c2d63e3f265caef9fb225", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b13fce5234c26dbd6c679ef95f4d9a2173d98089d45ddd2d5707ede1e593b6b0", "generation_seconds_batch": 14.85123584989924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4730606079101562, "target_z": 3.6875000136726555, "ce": 5.808161735534668, "genuineness": 3.911123275756836, "identity": 0.6377394199371338, "hypothesis": "La carretera gira a la izquierda atrás del puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.09523809523809523, "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/emo_Distress/0e2b0e8c4f0f4c6326124a318c279388a9c8b6c83b8c2d63e3f265caef9fb225.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "0e9b78ec47e8b8bc900b7cba4e5014de21773e66e518ce8dc0b8bbae90a710de", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c84e0829bb2ef7032b4dae0a39640b3ddbbf61c1e071cbe7e07f8c7edfc41e53", "generation_seconds_batch": 16.244832136901096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.732302188873291, "target_z": 2.781249874667326, "ce": 5.808161735534668, "genuineness": 4.118232727050781, "identity": 0.47633665800094604, "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/emo_Distress/0e9b78ec47e8b8bc900b7cba4e5014de21773e66e518ce8dc0b8bbae90a710de.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "0e9ed21c395cd944536e5b66fe6450265e85bc7c31690f263175f4ec74983b14", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8a7b54884e5e8e717462427dcf5dc3943a951dc68c3392bed6e43e765ad1fa76", "generation_seconds_batch": 20.564955975976773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8191261291503906, "target_z": 1.6640625301937806, "ce": 6.133810997009277, "genuineness": 3.8671910762786865, "identity": 0.3031831979751587, "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/emo_Distress/0e9ed21c395cd944536e5b66fe6450265e85bc7c31690f263175f4ec74983b14.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "0ea6c966e8bfd3a91d296df2e97586be0c7abfa2b9287464e1f72b4b33a5007a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5c8dd7c70afdc9be944a8d9d716b48b2c420bc70ab289be1506aac937bee0a59", "generation_seconds_batch": 20.103449468966573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.649308204650879, "genuineness": 3.773050308227539, "identity": 0.3035341501235962, "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/emo_Distress/0ea6c966e8bfd3a91d296df2e97586be0c7abfa2b9287464e1f72b4b33a5007a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "0ec4dbc3e1a3036b920e1ca37a92350c84eb63640b695dc7c08d1f9e14228ac4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bfa0340b881261d4932acce05edfc59275b42d300c736790369db2b5b2b1bda7", "generation_seconds_batch": 21.18437027197797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20510315895080566, "target_z": -0.3105468748575765, "ce": 6.157639026641846, "genuineness": 3.936227321624756, "identity": 0.45542073249816895, "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": 0.03999999999999915, "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/emo_Distress/0ec4dbc3e1a3036b920e1ca37a92350c84eb63640b695dc7c08d1f9e14228ac4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "0f2d22569cd7cecfb30135cc9dd4e07508fedbd18db553436e79078361e35e1d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4c08d31bafa8d6b62479e00529d1d9bceeba4c894ce8339497b2331381d91f2c", "generation_seconds_batch": 21.208039171993732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.923877716064453, "target_z": 3.015625001139388, "ce": 5.3514580726623535, "genuineness": 3.8922953605651855, "identity": 0.6524388790130615, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prête, t'étais cette inmeu. Dis-moi quand tu es prête.", "wer": 0.5555555555555556, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/0f2d22569cd7cecfb30135cc9dd4e07508fedbd18db553436e79078361e35e1d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "0f4559d66474ea545b1affe5ef9f03437424ea4cec04d822c0ff46db8717785b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "54988a6268afc2950d0768853397dee4f3549b4584d3a441e8d9a859843e7904", "generation_seconds_batch": 21.90512177196797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.617357015609741, "target_z": 2.6406249737940772, "ce": 6.0305562019348145, "genuineness": 4.406930446624756, "identity": 0.4361075162887573, "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/emo_Distress/0f4559d66474ea545b1affe5ef9f03437424ea4cec04d822c0ff46db8717785b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "0fde4a586a0fcd6a5a5051cc4bc1250708d3956372de443c535bb57ef001df7d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "31ca6005a36ef9276b3057386c5d2e8c784a464ca2f863ba346419143cd695cf", "generation_seconds_batch": 21.857947867945768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.396430253982544, "target_z": 3.593749788073842, "ce": 4.909646987915039, "genuineness": 3.2395870685577393, "identity": 0.30803608894348145, "hypothesis": "A door is still open. I I put your coat on the the chair. Tell me when you are ready.", "wer": 0.16666666666666666, "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/emo_Distress/0fde4a586a0fcd6a5a5051cc4bc1250708d3956372de443c535bb57ef001df7d.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": "10bcc5dfd38b11ba51e8bf53b9c7020c9d023221f99211708d56896333a030b9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1aad79c4ad449930202fa3c48dc7caacdb0005c4ca1f0387ca24276ea61ea87", "generation_seconds_batch": 22.38718523096759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.566270112991333, "target_z": 2.5781248233948686, "ce": 5.760505676269531, "genuineness": 3.9801597595214844, "identity": 0.6929953098297119, "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/emo_Distress/10bcc5dfd38b11ba51e8bf53b9c7020c9d023221f99211708d56896333a030b9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "10f0f2b6fac31eae4e0ed1ce0eb664b27e486a314f031c70dc9e22802867a9dd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e3dd2eee66b94a6f33bb95b7aa3ad83dccd5f498ca3701c1353a5ced1867ff9a", "generation_seconds_batch": 21.4854321150342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7706172466278076, "target_z": 2.8281248416250757, "ce": 5.557967185974121, "genuineness": 3.7918784618377686, "identity": 0.5683676600456238, "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/emo_Distress/10f0f2b6fac31eae4e0ed1ce0eb664b27e486a314f031c70dc9e22802867a9dd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "10f9a0a40b535f95ee8b5b2d76a2f8acc2b244218b25c4ebe5c22561ec7ca536", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ed59d1fff33b24666fed7753dc9b9f9e922af885dda1bc1fa28fcd643e3fde7b", "generation_seconds_batch": 23.0926042990759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276854991912842, "target_z": 1.7968749851879566, "ce": 5.982900142669678, "genuineness": 3.9801597595214844, "identity": 0.5673997402191162, "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/emo_Distress/10f9a0a40b535f95ee8b5b2d76a2f8acc2b244218b25c4ebe5c22561ec7ca536.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "1105e770dbf81a88e5271eb33205aeb6faa1028db29156d4a445ca1d2bc4d8f2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7fff556dad4e8e3146881b34c58e69a182400d96c9057779018fa96dd72896df", "generation_seconds_batch": 22.749968225019984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19392791390419006, "target_z": -0.3242187645271963, "ce": 5.990842819213867, "genuineness": 4.413206577301025, "identity": 0.5307759046554565, "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/emo_Distress/1105e770dbf81a88e5271eb33205aeb6faa1028db29156d4a445ca1d2bc4d8f2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "115fb74d6c6963ef8d2718b4dfe41f2599c0820452a1440464aba37ec2a4d50a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "67d19a229faaf291227b7036c5a20607bf01fd9c25b9f89e5ec31352cad55ec5", "generation_seconds_batch": 23.538451493019238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.119260787963867, "target_z": 2.0312498199767046, "ce": 5.982900142669678, "genuineness": 4.413206577301025, "identity": 0.3811773359775543, "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/emo_Distress/115fb74d6c6963ef8d2718b4dfe41f2599c0820452a1440464aba37ec2a4d50a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "118d933f7a102a475bc01051b104ee3fc094a8973ca433f469d6b2e7fbc18f74", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a27400253bb8533c94c4c170f5a1f3900791cdfc52ed4442a843c4c123c48ea1", "generation_seconds_batch": 16.129107884014957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2469778060913086, "target_z": 2.1874999042914127, "ce": 5.895530700683594, "genuineness": 3.9927117824554443, "identity": 0.5120495557785034, "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/emo_Distress/118d933f7a102a475bc01051b104ee3fc094a8973ca433f469d6b2e7fbc18f74.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "1190586e4a7963b599ed199fe2680e841cfae0dd1458f6ad4e9399a69d5951b0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4e0ff15a34ab2ddcbc9b8413a09b09313057662aa16537dca37640ff0ed6df28", "generation_seconds_batch": 15.421133280033246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0771379470825195, "target_z": 3.203124868970386, "ce": 5.720792293548584, "genuineness": 3.961331605911255, "identity": 0.1420854926109314, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "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/emo_Distress/1190586e4a7963b599ed199fe2680e841cfae0dd1458f6ad4e9399a69d5951b0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "12012130990b3e7da22d32cfa4079991118a111dcb71858d03ebae77dcbcb0d4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a1ffeeae11d70a08f82b8efe6ca035d24ce6ded75fe9cb48d1bbffbe99f1607e", "generation_seconds_batch": 21.03209709993098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.115453004837036, "target_z": 3.249999835928136, "ce": 5.422942161560059, "genuineness": 4.042920112609863, "identity": 0.4923604726791382, "hypothesis": "La puerta silla abierta. 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/emo_Distress/12012130990b3e7da22d32cfa4079991118a111dcb71858d03ebae77dcbcb0d4.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "3cf69f84cdb1647710b320bcfe2cc12e296811a5612fc53385e842c4dac3ebd3", "generation_seconds_batch": 16.580585776944645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1204906702041626, "target_z": -0.4140625119635734, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.6931973695755005, "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/emo_Distress/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1303293eb7c542f6e3c5ea2d4766ee21842a99b1fc31fe657681825ca850ed92", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "07897b23d6f2ded9274159ef9501c6536789ad20983a4b9b305aa7fcf206b7b0", "generation_seconds_batch": 22.003738892031834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16359513998031616, "target_z": -0.3613281376756909, "ce": 6.260893821716309, "genuineness": 4.281409740447998, "identity": 0.5835807919502258, "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/emo_Distress/1303293eb7c542f6e3c5ea2d4766ee21842a99b1fc31fe657681825ca850ed92.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "13673b60e1d1c3f62fe3531958b2d09cffde1ddb01bf878f6dd013be1a46868f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a94dbd5344e609e28da23a5702d821fb8dffc49be2d2932842c336c1e53c605b", "generation_seconds_batch": 22.11987629206851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2214343547821045, "target_z": 2.1562498290918084, "ce": 5.919358730316162, "genuineness": 4.15588903427124, "identity": 0.36958327889442444, "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/emo_Distress/13673b60e1d1c3f62fe3531958b2d09cffde1ddb01bf878f6dd013be1a46868f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "14288803b5f9d4f2f65782935bbf320481d86a8e6b76cb1ec6aa39ae4eb0299e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e1cb795a58865c833d51b95a03bba9c907ab7147d717a700ddaa1ebfadaae9db", "generation_seconds_batch": 19.231430392945185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6185867786407471, "target_z": 0.1953124960121422, "ce": 6.1020402908325195, "genuineness": 4.218649387359619, "identity": 0.38646990060806274, "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/emo_Distress/14288803b5f9d4f2f65782935bbf320481d86a8e6b76cb1ec6aa39ae4eb0299e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "147dec9512994b6a0af90dcde6694b2923377705cc33772710aaaf708ac89424", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7a45abe8759d198df020cdd1c1d2a3b573274ad54983a1c842585f9512ed0a7f", "generation_seconds_batch": 24.314007473061793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4768683910369873, "target_z": 2.468749997721224, "ce": 5.327630043029785, "genuineness": 4.18726921081543, "identity": 0.5700421333312988, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten. Ferntemi können gemeinsam hineinschauen.", "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/emo_Distress/147dec9512994b6a0af90dcde6694b2923377705cc33772710aaaf708ac89424.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "15579416f68134685328b4ff62f1c0cb923a4c27d308b36d667d6847ee019501", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7409388faf6a7740a74f39c403a29f7a13ada9102addb0f1a44e441dcfe77cc3", "generation_seconds_batch": 16.819153797929175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.821704149246216, "target_z": 2.8906249920242844, "ce": 5.414999485015869, "genuineness": 4.168440818786621, "identity": 0.5833162069320679, "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/emo_Distress/15579416f68134685328b4ff62f1c0cb923a4c27d308b36d667d6847ee019501.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "26d68bacedd19a0f2942ec65fe4628f72552f24aa58876e757f07ad7991ea553", "generation_seconds_batch": 16.00143401697278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14763054251670837, "target_z": -0.38085936175461516, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.587026059627533, "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/emo_Distress/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "15c251a8a609ff9dcfd49833a24bbfd4cf281b17a247fe5074a94137f4e15822", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dacaaf25f14a12464381f7c460e53142ac61a0c1d7b9831603e79603fa7026e6", "generation_seconds_batch": 20.54550458607264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.754037857055664, "target_z": 4.031249965818362, "ce": 5.649308204650879, "genuineness": 3.4969046115875244, "identity": 0.6224514842033386, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Mi tente será negócio por Venezuela, pero que asesino. ¡Te fuerte con él!", "wer": 0.8666666666666667, "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/emo_Distress/15c251a8a609ff9dcfd49833a24bbfd4cf281b17a247fe5074a94137f4e15822.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "15f7818ce2839b34941b8b8130c98a22c1c5c2dbc958d939f55b1054535355a6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "73df245b4257ab6e9f946f739b70ce4135d6921fe9bfc443b2f579c9593cb0c9", "generation_seconds_batch": 21.02232220210135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 6.1020402908325195, "genuineness": 4.137060642242432, "identity": 0.3721415102481842, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond. Het stond naast het oude raam. We kunnen daar samen in kijken.", "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/emo_Distress/15f7818ce2839b34941b8b8130c98a22c1c5c2dbc958d939f55b1054535355a6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "16246ecda10f8f6654baf49aab614c14292eb66b952d76a34bf69d1a9bdcf7bf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "70bd8e83328a4159c04858259748aea6d81686a766bbef72d90e2c6b1821810d", "generation_seconds_batch": 21.88226703298278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5802717208862305, "target_z": 0.1484375290543926, "ce": 5.919358730316162, "genuineness": 4.519899368286133, "identity": 0.7782394886016846, "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/emo_Distress/16246ecda10f8f6654baf49aab614c14292eb66b952d76a34bf69d1a9bdcf7bf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1670d0622dffbfdddd8ad9823ed827007da162913bf35ea7ec7a4c9e4e5c66c2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e6bd468293feacf8ceb9f651019dd8638f0135e030b955dcc51c4f96fe87c28c", "generation_seconds_batch": 21.304626634926535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5643070936203003, "target_z": 0.1289062685150541, "ce": 6.149696350097656, "genuineness": 3.6851859092712402, "identity": 0.447673499584198, "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/emo_Distress/1670d0622dffbfdddd8ad9823ed827007da162913bf35ea7ec7a4c9e4e5c66c2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "16a14f0be3063c522c1c93053830eb39bee358caea5e733895371a93957142a9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e56101a4b685debb341dd80edb2f0fc3e7d9b713fefc8514862e2c2b339b4ef2", "generation_seconds_batch": 22.161250276956707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.154016375541687, "target_z": -0.37304687941512826, "ce": 6.181467056274414, "genuineness": 4.7081804275512695, "identity": 0.5726423263549805, "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/emo_Distress/16a14f0be3063c522c1c93053830eb39bee358caea5e733895371a93957142a9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "16bb82198ff4a4250b3d06112c6ce287d73524a90d29ffe081a35291eee7efda", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e5acb6eaa0a3d81c40c8bae6115de101fbf58f3ac54c8864634e375c10b3fab8", "generation_seconds_batch": 23.096612227032892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.093717575073242, "target_z": 2.0000000364604142, "ce": 5.808161735534668, "genuineness": 4.262581825256348, "identity": 0.44365230202674866, "hypothesis": "De. De 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/emo_Distress/16bb82198ff4a4250b3d06112c6ce287d73524a90d29ffe081a35291eee7efda.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "17e233e6b44f039133130c9cbf4ed026610e34993fd14bb3bcc59984e7de01b1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5f59e8d062594c32986b8044dfc1ffb0b3cbe0b541a2e3c4e38f4023c5cffed7", "generation_seconds_batch": 23.130475674988702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.923877716064453, "target_z": 3.015625001139388, "ce": 5.359400749206543, "genuineness": 3.9048471450805664, "identity": 0.7468101978302002, "hypothesis": "La porte m'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/17e233e6b44f039133130c9cbf4ed026610e34993fd14bb3bcc59984e7de01b1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "17ff3a031247b6c107436c2528cee71572e9008f5b87ba5abd72c8e6c2f6b3ab", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0d1ea50de2c3b4435e260a3f84d6b04207465a5bd33dfc674172b0d6bbab5dd2", "generation_seconds_batch": 23.03192246798426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7463037371635437, "target_z": 0.35156250740602163, "ce": 6.038498878479004, "genuineness": 4.231201171875, "identity": 0.510910153388977, "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/emo_Distress/17ff3a031247b6c107436c2528cee71572e9008f5b87ba5abd72c8e6c2f6b3ab.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "1836130bb14e8b1828a5401fa2b5948edcd8972d468a1df4660bef0c32fdadc3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "861962190b28549e1a3c47e09bc74203fdcc6093b07b6183ba35340c9c9a578e", "generation_seconds_batch": 16.819153797929175, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.345343589782715, "target_z": 3.5312499293579473, "ce": 5.7247633934021, "genuineness": 4.017816066741943, "identity": 0.5255834460258484, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Siga, síganos. Dime cuándo estás listo.", "wer": 0.13333333333333333, "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/emo_Distress/1836130bb14e8b1828a5401fa2b5948edcd8972d468a1df4660bef0c32fdadc3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1862da24317bd2d7bb7416b6f3518d44766f696d071befc72b66027f120e3f28", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "8086aa4f99384cd0dfca980ee9a91cc200a2bdbc3b822c286b46aa599a1284f7", "generation_seconds_batch": 21.304626634926535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.695216953754425, "target_z": 0.28906250284846985, "ce": 5.847874641418457, "genuineness": 3.8922953605651855, "identity": 0.6132349371910095, "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/emo_Distress/1862da24317bd2d7bb7416b6f3518d44766f696d071befc72b66027f120e3f28.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": "186a69a89c5c68e69f29760911f089bba43ab31efca378c848c733ae84bdcd42", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1aab20a8dea15af022613cf7f582262484b4c19fc2bf5dc8910082dd4f9ba2fd", "generation_seconds_batch": 15.136669531930238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8957562446594238, "target_z": 1.7578124641092798, "ce": 6.24500846862793, "genuineness": 4.18099308013916, "identity": 0.5682278275489807, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand her neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "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/emo_Distress/186a69a89c5c68e69f29760911f089bba43ab31efca378c848c733ae84bdcd42.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "18dd3eeaf9d825597393bb193c11fccb090449dea20c5f1b5dddfb54175e65d7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1c878cd649c486355152e8789bb45ee54979b51d9db81a3d16318c87b8d23278", "generation_seconds_batch": 21.074514662963338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 5.990842819213867, "genuineness": 3.9425034523010254, "identity": 0.4598885476589203, "hypothesis": "De deur staat nog open. Ik. 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/emo_Distress/18dd3eeaf9d825597393bb193c11fccb090449dea20c5f1b5dddfb54175e65d7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "18defaf47fd3b4f7acd8cf80f8c556754e6c42c89624c981ed33f837b89e78c2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "210d5e55037a4069724f7cca43d377edf3c578292d83c2725da9c0bf147b5ebc", "generation_seconds_batch": 20.451534943073057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3146440982818604, "target_z": 1.0468749304973353, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.5994733572006226, "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/emo_Distress/18defaf47fd3b4f7acd8cf80f8c556754e6c42c89624c981ed33f837b89e78c2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "190020e98c4323f15d9d08fc79ed90afc56ab4162da54ad3290f7f10810d72f0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "556933b40349d8b05a30e83b8f73ed357cc2e15e0ab708181da885895a4624b3", "generation_seconds_batch": 21.68031800398603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.119260787963867, "target_z": 2.0312498199767046, "ce": 4.935460567474365, "genuineness": 3.8169827461242676, "identity": 0.5365152359008789, "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/emo_Distress/190020e98c4323f15d9d08fc79ed90afc56ab4162da54ad3290f7f10810d72f0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "190f54b7449429f2e0b4c760f0cbf058ba2bb43959ff5952f0a27f039694b637", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "cc87522e0215fd983ff5b323ca80786c346df0e1ea900ed2e91c65c324c9f3c6", "generation_seconds_batch": 24.314007473061793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 6.022613525390625, "genuineness": 4.017816066741943, "identity": 0.6251684427261353, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie. sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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/emo_Distress/190f54b7449429f2e0b4c760f0cbf058ba2bb43959ff5952f0a27f039694b637.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "19173536ac0d791087ef967acfb545747acf3183bc4f5b0e83587158fe8f4220", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ed2098cfd4ba31b26e3f2ea7a727873c3bbc91e6c7a9593450db944719a12355", "generation_seconds_batch": 21.519763472955674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3836586475372314, "target_z": 3.578124896315697, "ce": 4.400322914123535, "genuineness": 3.5188708305358887, "identity": 0.32974177598953247, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "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/emo_Distress/19173536ac0d791087ef967acfb545747acf3183bc4f5b0e83587158fe8f4220.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": "19a6276ecd4151e515282f72fbe326a97a855197b816f65f75c5bbc3191d4cbf", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2470f535176980aaabb7332a34fdd3153bb8fabedef504d516c0650dab458aab", "generation_seconds_batch": 15.481037138029933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6074115633964539, "target_z": 0.18164064280293662, "ce": 6.23706579208374, "genuineness": 4.024092197418213, "identity": 0.31380680203437805, "hypothesis": "Someone moved the little blue chair. It used stand here, beside the tall bookshelf. We can put it back after lunch.", "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/emo_Distress/19a6276ecd4151e515282f72fbe326a97a855197b816f65f75c5bbc3191d4cbf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "1a4183498ea2f2faeba3c2319f5877725f43f63a25dbaa802741c08570742224", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "875c21c03124c73e10bd4db889d14c0c99e0b77aaca3eab3f2907d33a4c2e35d", "generation_seconds_batch": 22.997691037948243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6467082500457764, "target_z": 1.4531250330422505, "ce": 5.307773113250732, "genuineness": 4.093128204345703, "identity": 0.39278921484947205, "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/emo_Distress/1a4183498ea2f2faeba3c2319f5877725f43f63a25dbaa802741c08570742224.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "1a76f1d4437cdb92c5e113b010dab40002cabeab447e032ed2bbfab1cd517f41", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "81822cb68018d0120181f210fc0dba5386955e5c2f6d03d81dec7c44ca713ae4", "generation_seconds_batch": 22.589896689984016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4349936544895172, "target_z": -0.029296890809007735, "ce": 6.316492557525635, "genuineness": 4.7081804275512695, "identity": 0.5037686824798584, "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/emo_Distress/1a76f1d4437cdb92c5e113b010dab40002cabeab447e032ed2bbfab1cd517f41.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "1b0d50fbc1ee79ce312a25f25c2e3640fa47829342ccb3098c6d7bce79be81bd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ede1850eccc536a5719e97468f1ec37e03510ecfbbf5f23c6293b7c98a4e8c9d", "generation_seconds_batch": 25.630187592003495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.613565921783447, "genuineness": 4.030367851257324, "identity": 0.44425898790359497, "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/emo_Distress/1b0d50fbc1ee79ce312a25f25c2e3640fa47829342ccb3098c6d7bce79be81bd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "1b4d73e20d8bba2e9317f36cfc24bc8b500661bb83d0b44e35375dded21d8603", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cd2b6db1581bdba5a08836adfb39d0dd0f729c74bbf26922c0630be18ae2454d", "generation_seconds_batch": 17.81304517108947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.706758737564087, "target_z": 2.7499997994677217, "ce": 6.038498878479004, "genuineness": 4.394378662109375, "identity": 0.36013588309288025, "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/emo_Distress/1b4d73e20d8bba2e9317f36cfc24bc8b500661bb83d0b44e35375dded21d8603.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "1b57b2dfbf81ee59b829f04f73a50ca1378718eaf1ab2b28123b7b79b0c14e2b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "19f8922d65a79ac296230ff0fab6103a905848fae2ec67bfca6f441d7abe84fb", "generation_seconds_batch": 22.080132103990763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1026813983917236, "target_z": 3.2343749441699905, "ce": 6.38003396987915, "genuineness": 3.7918784618377686, "identity": 0.6359377503395081, "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": 0.03999999999999915, "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/emo_Distress/1b57b2dfbf81ee59b829f04f73a50ca1378718eaf1ab2b28123b7b79b0c14e2b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "1b752b6254e3626ad198a66e8b9db3ef29442ada8969d9f70ff5c2a37ae62097", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "cd9b18aa9d7bfd46c8fcb31f0e849a230c27d6b58751b4ea1e8625a4d051ab88", "generation_seconds_batch": 23.281363464077003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.639092445373535, "target_z": 3.890624773261799, "ce": 5.689021587371826, "genuineness": 3.6287014484405518, "identity": 0.6063563823699951, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo y desde el comienzo. Tal vez sí. Dime cuándo estás listo.", "wer": 0.7333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/1b752b6254e3626ad198a66e8b9db3ef29442ada8969d9f70ff5c2a37ae62097.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1b9b17701805b8636f27b7701b8b04e477ddb5198124c8d5b7a13816100cf14c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c0d5580ae9560b1397730e488c9c57ed5ff207a7ba9c673b3c6a32419ced4600", "generation_seconds_batch": 23.118824679986574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2945050299167633, "target_z": -0.2011718668818609, "ce": 6.459460258483887, "genuineness": 4.080576419830322, "identity": 0.5750932693481445, "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/emo_Distress/1b9b17701805b8636f27b7701b8b04e477ddb5198124c8d5b7a13816100cf14c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "1bede3eb9b1e1b484d77e448a634a6ddd7d2792b85d64584e3539242608cdd6d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "01c4b649abccbec45065f8526f50d0be15aa4793d20e1bc4d4bd3507025ce75a", "generation_seconds_batch": 21.4854321150342, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1282248497009277, "target_z": 3.2656250193695953, "ce": 5.323658466339111, "genuineness": 3.7793264389038086, "identity": 0.5354994535446167, "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/emo_Distress/1bede3eb9b1e1b484d77e448a634a6ddd7d2792b85d64584e3539242608cdd6d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1c29baeaac570c4eff1352ed281d22eda054b143a5d1540b1e047eb18d4d73d2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "14cebb18eb86a5c66e1a04c55012affd26ce185f28eb478bc89c9710b2d496d4", "generation_seconds_batch": 22.608008089940995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23862886428833008, "target_z": -0.2695312423091314, "ce": 6.324435234069824, "genuineness": 4.381826400756836, "identity": 0.3525615930557251, "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/emo_Distress/1c29baeaac570c4eff1352ed281d22eda054b143a5d1540b1e047eb18d4d73d2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1cde705b70a451840e8262f290f41dcf4ff240380107a09d22fc3587c1bfee3b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4f0e02f9cbdd99b84ca0a5d5214379aa6c08d10129d58e555caedd81c57fd8b0", "generation_seconds_batch": 24.51027756300755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4493618309497833, "target_z": -0.0117187417394374, "ce": 5.637393951416016, "genuineness": 3.747946262359619, "identity": 0.30381256341934204, "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/emo_Distress/1cde705b70a451840e8262f290f41dcf4ff240380107a09d22fc3587c1bfee3b.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "302761a1caa41e15cc42c9597fe983cdf12f65d36f1f05a1c58fe97df36dda4e", "generation_seconds_batch": 16.20539846306201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059825122356414795, "target_z": -0.4882812582605626, "ce": 6.2767791748046875, "genuineness": 4.394378662109375, "identity": 0.6618750691413879, "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/emo_Distress/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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "6b0754c23d7e07081548a7c424cbb331ce25c6fad2773ddc2d5490088c9b05d5", "generation_seconds_batch": 17.173563727061264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11091190576553345, "target_z": -0.42578125370301084, "ce": 6.308549880981445, "genuineness": 4.557555198669434, "identity": 0.37677106261253357, "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/emo_Distress/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "1d93872d5216fcdcb680757e94c2632af2c0404e6e6f6bc9ba47b1a861a570c6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0a223753b700991956464409afaacbc2d97ad4e601e7bab6858d88300b63c4a1", "generation_seconds_batch": 21.446575654903427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7143744826316833, "target_z": 0.31249998632734466, "ce": 5.8875885009765625, "genuineness": 4.3881025314331055, "identity": 0.4565621018409729, "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/emo_Distress/1d93872d5216fcdcb680757e94c2632af2c0404e6e6f6bc9ba47b1a861a570c6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "1dd3048112a4454e4bb1b4f44869622c001203ce80f542d3ed21018f557b4e55", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d5e838bfe5d545f6d0986bb195a83e4b0573c745cdb63d40ac46ce81be14ff3", "generation_seconds_batch": 22.213588834973052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6321567296981812, "target_z": 0.21191408934682845, "ce": 6.260893821716309, "genuineness": 4.6203155517578125, "identity": 0.4086853265762329, "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/emo_Distress/1dd3048112a4454e4bb1b4f44869622c001203ce80f542d3ed21018f557b4e55.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "1e0db2cc24678b7976c1bc6b70db73e2689e16e0575fe056ad5c136054bd6129", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6f7813c976a70be7102078acf2a91bf2fceb1e9d974a390bf04e112f043df7c7", "generation_seconds_batch": 14.34858529700432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.681215524673462, "target_z": 2.7187500159514313, "ce": 5.839932441711426, "genuineness": 4.017816066741943, "identity": 0.5506174564361572, "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/emo_Distress/1e0db2cc24678b7976c1bc6b70db73e2689e16e0575fe056ad5c136054bd6129.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "1e20884d44358bc294699fea31ca0b9b197c775f1d0c37314063195178d6911f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b2b50856fbdfb9c948bced3c33cecd1301bd543ea6df63261ff1925a995c8e17", "generation_seconds_batch": 20.693881597951986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2769439220428467, "target_z": -0.22265627535138177, "ce": 6.022613525390625, "genuineness": 4.331617832183838, "identity": 0.4351591467857361, "hypothesis": "La porte étant encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/1e20884d44358bc294699fea31ca0b9b197c775f1d0c37314063195178d6911f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "1e33e3bbd492b943e0c639b33bcbce834ff6969eedcf812168ecba9a8e68a127", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "76462c0d20e545a2741cc66e27944d0546a02c117f2115db505fa0beeb6ce103", "generation_seconds_batch": 21.474965133005753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07578974962234497, "target_z": -0.4687499977212241, "ce": 6.300607204437256, "genuineness": 4.607763767242432, "identity": 0.5657476186752319, "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/emo_Distress/1e33e3bbd492b943e0c639b33bcbce834ff6969eedcf812168ecba9a8e68a127.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "1e4d3c68536be8a58b7c1f44276bd30f478e9b01ec93cc9711f7ae2ba97bfcad", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "43e30df6e294325e68e06f7ee7979c36eb41cdab3e63bf7abcc6e092993693b5", "generation_seconds_batch": 21.439444393035956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06301805377006531, "target_z": -0.4843749988606121, "ce": 6.507116317749023, "genuineness": 4.507347106933594, "identity": 0.6299383640289307, "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/emo_Distress/1e4d3c68536be8a58b7c1f44276bd30f478e9b01ec93cc9711f7ae2ba97bfcad.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": "1e8791946153ac85d6837e5a040c154573958df9e7980a547119ccaeccb174bc", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12d5800974e3203fd1715e0be7eb4e85fda64daf66be36df817ac8ea6ede3836", "generation_seconds_batch": 16.55699996300973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.808932304382324, "target_z": 2.8749998085828254, "ce": 6.062326908111572, "genuineness": 4.068024158477783, "identity": 0.6126284599304199, "hypothesis": "The keys are on the kitchen table. I checked the door and looked beside the window. Take them with you when you leave.", "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/emo_Distress/1e8791946153ac85d6837e5a040c154573958df9e7980a547119ccaeccb174bc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "1e9524d4c39791299ed972ab33c392d2f33e286bfd2824783a3f26a2f8a64067", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "53770c9b0ba713b438a76be8dd3df91af1441883f0fd9653038979c8dc8eeaa1", "generation_seconds_batch": 22.93178117100615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20829609036445618, "target_z": -0.30664061545762594, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.5308057069778442, "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/emo_Distress/1e9524d4c39791299ed972ab33c392d2f33e286bfd2824783a3f26a2f8a64067.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "f3660ef085090185e824008f1f2fc0637898cb4aa37f6a6e5b1c0d8e6d11ad87", "generation_seconds_batch": 16.20539846306201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.348263263702393, "genuineness": 4.432034492492676, "identity": 0.531059741973877, "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/emo_Distress/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "1eefb14979add6ed21b1f8ee575cacfcefde413079fb952673ca08f8f5eecb1d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a141befe7a45f540c07a9849999722f054b73f577db5185598ba4df57b68a0d1", "generation_seconds_batch": 21.003098550019786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09654375910758972, "target_z": -0.44335936631216694, "ce": 6.141753673553467, "genuineness": 4.758388519287109, "identity": 0.5617457628250122, "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/emo_Distress/1eefb14979add6ed21b1f8ee575cacfcefde413079fb952673ca08f8f5eecb1d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "1ef3a787d01d26bb607478bfa860590269d0aa56873b1da46f9fdeec52b7ad43", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "081dfcff0747cb2ddea65e0f26820c1732948c3e81aff15699b6c9aab399c2bc", "generation_seconds_batch": 22.023857612046413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38071396946907043, "target_z": -0.09570311830609582, "ce": 5.990842819213867, "genuineness": 4.607763767242432, "identity": 0.5283942222595215, "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/emo_Distress/1ef3a787d01d26bb607478bfa860590269d0aa56873b1da46f9fdeec52b7ad43.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "1f044915524421b2a7bcbaa44cfae06d47556f061e9506e599e1f510d5fab585", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "01f1e8b4c775aecdcb6fcefcdd12fec69ae0d717b920fc0b0d5f8c650340789f", "generation_seconds_batch": 21.853147260961123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.75526762008667, "target_z": 1.5859374880364265, "ce": 5.77639102935791, "genuineness": 3.911123275756836, "identity": 0.5308014154434204, "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/emo_Distress/1f044915524421b2a7bcbaa44cfae06d47556f061e9506e599e1f510d5fab585.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "1f4200221b15fdf7024d9c0e54b9c605304848143c8f064b6f0563eb834bb3e8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6d32ba2009b9ea56294f1528911bcb990caefd5368168d3609a5d8fd26d76cc0", "generation_seconds_batch": 22.749968225019984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.8424209356307983, "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/emo_Distress/1f4200221b15fdf7024d9c0e54b9c605304848143c8f064b6f0563eb834bb3e8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "1fd6676db55dd175a71cb04c2306f113dd3df4141b8cd9d2f072848892be8755", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ae44f02999eb6e6f3c40572ac1b5c9ecdde582315fba6dcf210648dbdb647d5d", "generation_seconds_batch": 22.511927800020203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.923877716064453, "target_z": 3.015625001139388, "ce": 5.673136234283447, "genuineness": 4.15588903427124, "identity": 0.7984476089477539, "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/emo_Distress/1fd6676db55dd175a71cb04c2306f113dd3df4141b8cd9d2f072848892be8755.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "201ac0e0f3e46177d9975a7aea01db32fc27f9b7aed798a64a9a8904cb2f2c1f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f957b8ddf27b931245f7b59d0f7296b4de24b6fd9d757ee76d1b4013a603164f", "generation_seconds_batch": 20.945069725974463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42461666464805603, "target_z": -0.041992188283329214, "ce": 5.998785495758057, "genuineness": 4.080576419830322, "identity": 0.6562989950180054, "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/emo_Distress/201ac0e0f3e46177d9975a7aea01db32fc27f9b7aed798a64a9a8904cb2f2c1f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "2086f5d40918eb9cf308405e76c68b74bf91df6a69cd2316539f71da34f3672a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6b5ea2fa0145acc27e6f4156082f692df292cd5a4e9be5114673027266706958", "generation_seconds_batch": 19.999525881023146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7450737953186035, "target_z": 2.7968747664254714, "ce": 5.3514580726623535, "genuineness": 4.13078498840332, "identity": 0.6186248064041138, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu apprêts.", "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/emo_Distress/2086f5d40918eb9cf308405e76c68b74bf91df6a69cd2316539f71da34f3672a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "20ed4c2999447b7ae89dee70baa576ec7065923b9b7edcb5e17a0340a3834402", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dfecbfcc75d78b1986cef7b4dcfd45efa259f3209de6910b022b5d281ab32e55", "generation_seconds_batch": 16.18180844699964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.511375665664673, "target_z": 3.7343749806304047, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.38226988911628723, "hypothesis": "Ich habe dir keine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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/emo_Distress/20ed4c2999447b7ae89dee70baa576ec7065923b9b7edcb5e17a0340a3834402.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "2235650009cf393cdd737a0b18c3cdec12537fc2cc0a671c05f07080c13913ab", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "793f46b60c76bc77d47ffac1233bc38aa1c2e85f4d16ba17aec0fd14fad8401d", "generation_seconds_batch": 22.53241194493603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8702129125595093, "target_z": 1.7265625347513323, "ce": 6.173524379730225, "genuineness": 3.9801597595214844, "identity": 0.584823727607727, "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": 0.03999999999999915, "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/emo_Distress/2235650009cf393cdd737a0b18c3cdec12537fc2cc0a671c05f07080c13913ab.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": "224e399ed1c24f5897902b1bf8709b754b0fd1bf7317d8b921705137a8d40b86", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6bf8e71143bbcf85d3049e57041430c69ade487f824d68a1bd172227d7f82282", "generation_seconds_batch": 22.15724755206611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9366493225097656, "target_z": 3.031249892897533, "ce": 5.816103935241699, "genuineness": 3.7040140628814697, "identity": -0.044701725244522095, "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": 0.03999999999999915, "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/emo_Distress/224e399ed1c24f5897902b1bf8709b754b0fd1bf7317d8b921705137a8d40b86.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "2267e3eff5e40e36458baebb3dd8a93ea5a6bc93b30a19f3d2d0730f9d0748b4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c2543722c2255e34a949b28109cea75bcb2820a9051cde0ce54c00ce37191a2f", "generation_seconds_batch": 22.594514325028285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3836586475372314, "target_z": 3.578124896315697, "ce": 5.279973983764648, "genuineness": 3.4843525886535645, "identity": 0.5528035163879395, "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/emo_Distress/2267e3eff5e40e36458baebb3dd8a93ea5a6bc93b30a19f3d2d0730f9d0748b4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "226febc69502adc5e03e9ead626b73e7f32e9d9fafbf11d4fdeb130fab75b30d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1b2a09050d9d1b6929c8aeec1757aeb7f3acfab689df15eb14820490e66873dc", "generation_seconds_batch": 20.67262819199823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5509204864501953, "target_z": 1.3359374698062194, "ce": 5.998785495758057, "genuineness": 4.15588903427124, "identity": 0.7960155010223389, "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/emo_Distress/226febc69502adc5e03e9ead626b73e7f32e9d9fafbf11d4fdeb130fab75b30d.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": "227b1849ee72be8643ba0081ea3ceb81d100f2d391cdad8ef63ef2ab37dcf289", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70e85a3c586cc6b91af856e02e99acb7669b120d310244a08685347361d4bc2c", "generation_seconds_batch": 19.82278469100129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2469778060913086, "target_z": 2.1874999042914127, "ce": 5.967014789581299, "genuineness": 3.5847692489624023, "identity": 0.5902255773544312, "hypothesis": "Someone moved the little blue chair. It used to stand here. Beside the doll bookshelf. We can put it back after lunch.", "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/emo_Distress/227b1849ee72be8643ba0081ea3ceb81d100f2d391cdad8ef63ef2ab37dcf289.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": "23aac7adddb827ca4cabeb3345c4677f437940ed22120bb89f7ea2622ea51bb8", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30f53a7896854146c60dcd100d788b6ed668635e305ace5dcbbe9f1553666ad9", "generation_seconds_batch": 25.090171106974594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.25594162940979, "target_z": 3.421874812000989, "ce": 5.657250881195068, "genuineness": 3.6663577556610107, "identity": 0.47309380769729614, "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/emo_Distress/23aac7adddb827ca4cabeb3345c4677f437940ed22120bb89f7ea2622ea51bb8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "246f71cb5d3738de13a8fa7d12e91181dbcfbb87402cb07a9ebf7adb4de5b4dc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "265fd83ec6e26f74c0d99bf156abc6cf2496bd5546fd67226ee53ca599209cf3", "generation_seconds_batch": 26.07599109702278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7271461486816406, "target_z": 0.3281249510063184, "ce": 6.117925643920898, "genuineness": 4.595211505889893, "identity": 0.7913174629211426, "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/emo_Distress/246f71cb5d3738de13a8fa7d12e91181dbcfbb87402cb07a9ebf7adb4de5b4dc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "24f89c6cbca4842081e46014b85c583c582bcfdcc51e545c19672c50fa5f0616", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b0e66ad4048e0af97f78f8a512d7daf9a7f9be6a0f393fb7067721b4a7425cf9", "generation_seconds_batch": 19.87568703503348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0368597507476807, "target_z": 0.7070312012911654, "ce": 5.577824115753174, "genuineness": 3.653805732727051, "identity": 0.4927397072315216, "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/emo_Distress/24f89c6cbca4842081e46014b85c583c582bcfdcc51e545c19672c50fa5f0616.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": "25141ae358b571d038421387a4147e3f0e0d54ef6993ae5b45582adec7446701", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c05a730baabf34a0a2173f12cbde5a1ef4ccb75718a470a7d2ebdb5c40b8281", "generation_seconds_batch": 15.142696383991279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.137188911437988, "target_z": 4.5000002187624855, "ce": 5.744620323181152, "genuineness": 3.722842216491699, "identity": 0.6473150849342346, "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/emo_Distress/25141ae358b571d038421387a4147e3f0e0d54ef6993ae5b45582adec7446701.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "2578af22eee4cf2ba569ecc4fc9957728666acffcd49fff41a528eeb7cb6abb5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6e2e3e11d5a75f129f20faa4aaa835f14f1b291dbcfcb829aa5cc32f77e64a3a", "generation_seconds_batch": 21.07076871301979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4934478998184204, "target_z": 1.265625019369595, "ce": 5.299830436706543, "genuineness": 4.21237325668335, "identity": 0.6104376316070557, "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/manual-comparison-v1/audio/emo_Distress/2578af22eee4cf2ba569ecc4fc9957728666acffcd49fff41a528eeb7cb6abb5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "2682aaa072556f6cfe4fb80dcc2eb5a5684ff50c93bcbb287359d1c75a525b8a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "34c6fdf4a29bb7587363b20fe51876f94bacc3de0dd8c7ebbc8a8aa179d8a4cf", "generation_seconds_batch": 21.92765883798711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.447517156600952, "target_z": 3.656249938473051, "ce": 5.657250881195068, "genuineness": 3.8797430992126465, "identity": 0.6586495637893677, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête, la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/2682aaa072556f6cfe4fb80dcc2eb5a5684ff50c93bcbb287359d1c75a525b8a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "26849552dac72c211fded9ca1368acf5bb45d2008552f7b595f704eb05efb745", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "acf4eec5a59b24b4bd3e567cf509e0d205cff5e5d59a1d198d9b4ba95c723d29", "generation_seconds_batch": 15.598624182981439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.323607921600342, "target_z": 2.2812498382069117, "ce": 5.2223896980285645, "genuineness": 4.024092197418213, "identity": 0.4823744297027588, "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/emo_Distress/26849552dac72c211fded9ca1368acf5bb45d2008552f7b595f704eb05efb745.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "26851245cd3621f55ef0bb9f313e9e0328e94eb16f28c46746eaab6031a442e9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "04eed6b86e5eec78d3526a52ab67926d62be195ac1cf378b6d07d20d4c76aa74", "generation_seconds_batch": 20.96919816196896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.421973705291748, "target_z": 3.624999863273447, "ce": 5.33954381942749, "genuineness": 3.7291181087493896, "identity": 0.10322877764701843, "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/emo_Distress/26851245cd3621f55ef0bb9f313e9e0328e94eb16f28c46746eaab6031a442e9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "26c43c021fb60c02ff4cb230e92a569e743e277319e7e771ba8e8a41b7dc4abe", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b9f8902f4b0c625f166ef00590c24220356684b4e5e5cf2f4bde83ee25ece817", "generation_seconds_batch": 21.54455684009008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17796331644058228, "target_z": -0.34374998860612055, "ce": 6.181467056274414, "genuineness": 4.049196243286133, "identity": 0.368074506521225, "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": 0.03999999999999915, "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/emo_Distress/26c43c021fb60c02ff4cb230e92a569e743e277319e7e771ba8e8a41b7dc4abe.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "8bccf89d81b8bdec0a3d9f646446878348d46deabe3986892c24f295d3b9b067", "generation_seconds_batch": 14.933972772094421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13645529747009277, "target_z": -0.39453125142423495, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.3896593451499939, "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/emo_Distress/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "26e60036d05ba6bae0bacfb966a0127b26f5198760dd38a07ce76e96d496ddb4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4efd42552f6191482a77cfbc8e9ee17ab64d2694773b2aff6d50c8fe513fccc7", "generation_seconds_batch": 22.024435746949166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.617357015609741, "target_z": 2.6406249737940772, "ce": 5.9431867599487305, "genuineness": 4.068024158477783, "identity": 0.3984888195991516, "hypothesis": "De deur staat nog open. Ik heb je. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "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/emo_Distress/26e60036d05ba6bae0bacfb966a0127b26f5198760dd38a07ce76e96d496ddb4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "276dd27f0cd2c1fcda0b8d54501e2115dd09ea01bdabf2b0d2f1a0876131ff2e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8a7ce7865cc3e51cd3e95fea13cf219e64019f0106622cd14edd7067d2ca7c9c", "generation_seconds_batch": 22.05221380002331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11410483717918396, "target_z": -0.4218749943030603, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.5454978346824646, "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/emo_Distress/276dd27f0cd2c1fcda0b8d54501e2115dd09ea01bdabf2b0d2f1a0876131ff2e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "283d6bed7e057778d7c1352fdd10ce0d8f5b547ad4692c2d69b7a1cc1b8fd37d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "836657906ba5af4e04ac6e50c8a6f3dd1319e3837850ea2928665aca4077c855", "generation_seconds_batch": 19.77973629999906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 4.97020959854126, "genuineness": 3.6663577556610107, "identity": 0.6372883319854736, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête. près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "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/emo_Distress/283d6bed7e057778d7c1352fdd10ce0d8f5b547ad4692c2d69b7a1cc1b8fd37d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "290a12d4622a56551ca8e6c235dc5a5da69d48e01792eb113277733625f6e7a3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9d7d112ec4f704a931594d6a43745a4b3e9b38e8f1e5a2bcdf6d1c094c0ecb50", "generation_seconds_batch": 20.130076940986328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11410483717918396, "target_z": -0.4218749943030603, "ce": 6.221180438995361, "genuineness": 4.6956281661987305, "identity": 0.6353883743286133, "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/emo_Distress/290a12d4622a56551ca8e6c235dc5a5da69d48e01792eb113277733625f6e7a3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "2925157dc6a0b2d85405c0d0374ebb735de532536b951bb412669dc6e87758af", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "acddf62c7629637b1c3c104e55db5499f7d54b316f14a7a005b7e7169ef0cc9f", "generation_seconds_batch": 20.657408007071353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3966785669326782, "target_z": -0.07617189422717156, "ce": 5.728734970092773, "genuineness": 4.406930446624756, "identity": 0.5805927515029907, "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/emo_Distress/2925157dc6a0b2d85405c0d0374ebb735de532536b951bb412669dc6e87758af.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": "292bfcef2b1b07972113f807f0a390cf2dd5eeb3b07e07f94c5bee544c682a90", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d747f20adce48f7247ee8f992b95200f28f47ec0d8ad5b88a05f2aa93e2bfb2d", "generation_seconds_batch": 18.6053647340741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0847536325454712, "target_z": 0.7656249829091808, "ce": 6.38003396987915, "genuineness": 4.256305694580078, "identity": 0.45014718174934387, "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/emo_Distress/292bfcef2b1b07972113f807f0a390cf2dd5eeb3b07e07f94c5bee544c682a90.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "2a2911bc0f87e840adc4f937857025324977b3aafbd623e5402bbc9e15573f62", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "153da95592192f3a0a3c39e3e13ae9993f10bfb9f106ef43189f74168c846598", "generation_seconds_batch": 16.325589043088257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9953517913818359, "target_z": 0.6562500113938794, "ce": 6.09409761428833, "genuineness": 4.143336772918701, "identity": 0.629423201084137, "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/emo_Distress/2a2911bc0f87e840adc4f937857025324977b3aafbd623e5402bbc9e15573f62.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "2a76cf695a5a67cbe37748ea6682d13f9a99843801392ac57faca08bf2dbb46e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "875321f41a1fea091ac899e3540d448ce9e70db8e8d69132871e8ce6ccb80d25", "generation_seconds_batch": 22.542745109065436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1619986891746521, "target_z": -0.36328124914545906, "ce": 6.022613525390625, "genuineness": 4.1998209953308105, "identity": 0.6977990865707397, "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/emo_Distress/2a76cf695a5a67cbe37748ea6682d13f9a99843801392ac57faca08bf2dbb46e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "2a9d048346b721efa4e75ce7ac54a93b0d9babb279cda9d2a8be8fdd27e860d5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bde1fbf60465b62961dbc2defef679c503472800ff3082454bbacc184ac547a7", "generation_seconds_batch": 19.430499386042356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.269759863615036, "target_z": -0.2314453134257527, "ce": 5.982900142669678, "genuineness": 4.582659721374512, "identity": 0.48515555262565613, "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/emo_Distress/2a9d048346b721efa4e75ce7ac54a93b0d9babb279cda9d2a8be8fdd27e860d5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "2ada63056ebe042b22bd9dcb4b5a182bc3e127869e99ca96d313cd9401aac5b7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9da5146b6549b020db2f3c64639cbc1893ee7161639958f0af2cdb308cf67747", "generation_seconds_batch": 21.491574328043498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1741554737091064, "target_z": 0.8749999544244822, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.7537866234779358, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble quelque chose.", "wer": 0.15789473684210525, "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/emo_Distress/2ada63056ebe042b22bd9dcb4b5a182bc3e127869e99ca96d313cd9401aac5b7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "2af46f554ddeb6624234353d11f0cf8381aee6cfeb7605b7723592bf49feb973", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9453d357750882f22f9a86c5115f6335aaf0f2eefc451ccddc1b327f0976f2ef", "generation_seconds_batch": 17.05008179601282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4640965461730957, "target_z": 2.453124814279765, "ce": 5.7406487464904785, "genuineness": 3.9425034523010254, "identity": 0.4364398717880249, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen. Reit!", "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/emo_Distress/2af46f554ddeb6624234353d11f0cf8381aee6cfeb7605b7723592bf49feb973.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "2b4bee4be67db756017ebfa3aa01b4604c81457996e8fee58f1432325134200d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4006fe095b7238e448746f74f1c790ed5d7aa8cba19f37aa427c7f395c4165c6", "generation_seconds_batch": 21.368085636990145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1448042392730713, "target_z": 2.062499895176309, "ce": 5.824047088623047, "genuineness": 4.243753433227539, "identity": 0.692413330078125, "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/manual-comparison-v1/audio/emo_Distress/2b4bee4be67db756017ebfa3aa01b4604c81457996e8fee58f1432325134200d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "2b6dcc5e823919d19b4ab02f0941368bcd4ac34d582059dcc52708e62f5ced5f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0900ba3b6cb3a85c8e1f9c5607d43c1dadec1497323b5b3be9c7d377a463d74b", "generation_seconds_batch": 22.376354706007987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.779581069946289, "target_z": 4.062499749334652, "ce": 5.5539960861206055, "genuineness": 3.653805732727051, "identity": 0.5953679084777832, "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/emo_Distress/2b6dcc5e823919d19b4ab02f0941368bcd4ac34d582059dcc52708e62f5ced5f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "2b8f22718f0f2a8f7952b9602f24876d09e92ba5a296b6637006e5b96d1b84bb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "60b7f34e911d8b80a8e64c5548d4eac1e54f8258c8b8f1e2a54bf1c54f413518", "generation_seconds_batch": 23.067785097984597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.37469482421875, "target_z": 2.3437499886061204, "ce": 5.9431867599487305, "genuineness": 4.042920112609863, "identity": 0.2805681824684143, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "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/emo_Distress/2b8f22718f0f2a8f7952b9602f24876d09e92ba5a296b6637006e5b96d1b84bb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "2bb33976d4225300598d1410db9a4d3ab3dd7d79ab327e3afd25a52ef7a268ef", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0d87e702a42353ddc7e988f5037962326d3fb9bc30929450518b2cd4b7a0bb07", "generation_seconds_batch": 22.47029746393673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5790419578552246, "target_z": 2.5937500068363275, "ce": 5.4666266441345215, "genuineness": 3.898571252822876, "identity": 0.7958650588989258, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête. La fuille en fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "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/emo_Distress/2bb33976d4225300598d1410db9a4d3ab3dd7d79ab327e3afd25a52ef7a268ef.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "2bb5501870b828dc1eb9367f068d2610db271fdc9fd594a3c1e1dbbf19778db9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "aaf9cb982a4c8e65907da6b90de1a02d68c788ca27ef8de10bff30df14c0e7bf", "generation_seconds_batch": 23.2356517650187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.157639026641846, "genuineness": 4.6956281661987305, "identity": 0.555094301700592, "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/emo_Distress/2bb5501870b828dc1eb9367f068d2610db271fdc9fd594a3c1e1dbbf19778db9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "2bf8d5b1b044d19d677d24268f9d32776b039b055d0c31005907ef96bacf42b5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "27748fe6fe393e9761cc04db031744ba8737551079dfe558e35f585d9e3d5601", "generation_seconds_batch": 19.89310020301491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29290854930877686, "target_z": -0.2031250148120433, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.7089440822601318, "hypothesis": "I f found Little Box. It was beside the old window. We can look inside together.", "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/emo_Distress/2bf8d5b1b044d19d677d24268f9d32776b039b055d0c31005907ef96bacf42b5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "2c69f266ee77909a7024099765847a3bdf25960ec50de1fc8395b555e44cfa80", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1c99fbb6bf80aa575cbac49bc1732e60b759b3fb6d01e1d9a5cbde0ec754d40f", "generation_seconds_batch": 22.997691037948243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602007269859314, "target_z": 1.3984374743637713, "ce": 5.144948482513428, "genuineness": 4.093128204345703, "identity": 0.3897978663444519, "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/emo_Distress/2c69f266ee77909a7024099765847a3bdf25960ec50de1fc8395b555e44cfa80.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": "2cf2d4bbead1c61850ff171099d554370f8d2744c99766219201f04ce19d6e3f", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab5503eb6a15d1433a873c9c47ad5dffa1d81020fd08f4e8a7816d1d3adae29a", "generation_seconds_batch": 15.481037138029933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3599599599838257, "target_z": -0.12109374971515302, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.35036924481391907, "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/emo_Distress/2cf2d4bbead1c61850ff171099d554370f8d2744c99766219201f04ce19d6e3f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "2d1d6e8d8ac9dc8a3c4b852c54ffbc69e82a594ffb09b1d7c8efa60bb7e77b26", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "57db05a8db2ce0b3e7a7c42d73695a3d9c969621ad825c5b80d7785b25987195", "generation_seconds_batch": 21.41895077296067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2597496509552, "target_z": 2.2031250877328716, "ce": 5.665193557739258, "genuineness": 4.319066047668457, "identity": 0.8138081431388855, "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/emo_Distress/2d1d6e8d8ac9dc8a3c4b852c54ffbc69e82a594ffb09b1d7c8efa60bb7e77b26.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "2d87ac9f5e82440d57d87b8e39ca130fd4403f1073a0e14cea0b2271c89b793f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "97dc13a322b351b92230a928b06df581386fa8b45dfb6aa89736b9038d900272", "generation_seconds_batch": 21.474965133005753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09335082769393921, "target_z": -0.4472656257121175, "ce": 6.070269584655762, "genuineness": 4.7458367347717285, "identity": 0.6886403560638428, "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/emo_Distress/2d87ac9f5e82440d57d87b8e39ca130fd4403f1073a0e14cea0b2271c89b793f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "2df1ce27cb13210a3ca971ea67fdcc4786a7ecd95be34a55b666080cc22e4627", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d28a62ccf5d51cf44c11b5f9beb5a281ba46e60384c73e0e995c788a89b4fff6", "generation_seconds_batch": 17.2802964260336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.046441555023193, "genuineness": 4.3504462242126465, "identity": 0.33649808168411255, "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/emo_Distress/2df1ce27cb13210a3ca971ea67fdcc4786a7ecd95be34a55b666080cc22e4627.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": "2e739a79ee750503cf156be8a40367972ae4d9a2467c0c90ea5156c5adffd515", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fcafd3e4abf4193d651574f8411867a07362b48ac4dcc153ab44de22a1b16bac", "generation_seconds_batch": 22.34894807008095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.732302188873291, "target_z": 2.781249874667326, "ce": 5.879645347595215, "genuineness": 3.898571252822876, "identity": 0.5088801383972168, "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": 0.03999999999999915, "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/emo_Distress/2e739a79ee750503cf156be8a40367972ae4d9a2467c0c90ea5156c5adffd515.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "2e8a1e3fc854965697eea2648bfc8f57afac5fe615ac3a44951ca2dfda930488", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "652cdda4aebc03ed0a6695a5bdd6a7de90dd43de26c25b3622e25638a92b20ea", "generation_seconds_batch": 22.03762281697709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6045851707458496, "target_z": 2.6249997903526183, "ce": 5.796247482299805, "genuineness": 3.9550557136535645, "identity": 0.016176998615264893, "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/emo_Distress/2e8a1e3fc854965697eea2648bfc8f57afac5fe615ac3a44951ca2dfda930488.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "2e94aa6c9ff5533d71ca42534b7088d21dac0b99f80398bd13d39575a8de9156", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3ee60dae16f57a707117266e589c7aa7ca0a233a2145ae023921e9dcc963619d", "generation_seconds_batch": 15.89495463098865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276854991912842, "target_z": 1.7968749851879566, "ce": 6.0305562019348145, "genuineness": 4.005263805389404, "identity": 0.3735705018043518, "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/emo_Distress/2e94aa6c9ff5533d71ca42534b7088d21dac0b99f80398bd13d39575a8de9156.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "2eecc7472ed337e455a741e558d91e6becf86244276c809b00bb109969c97f70", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "24a9f009e44aa01d93775cc77f54b207873763a26e34fa60a78364a9211318b1", "generation_seconds_batch": 21.633088954957202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.154016375541687, "target_z": -0.37304687941512826, "ce": 6.141753673553467, "genuineness": 4.1998209953308105, "identity": 0.38727492094039917, "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/emo_Distress/2eecc7472ed337e455a741e558d91e6becf86244276c809b00bb109969c97f70.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "2f11c3ff647320bffe4cced7493cea68faa69233589ac9906ce756f7bdd241f1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "90825e4599853c4a86d6e4ac9bfdf7d79ea4cd108a49c09009763a355747b286", "generation_seconds_batch": 22.528873822069727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1958911418914795, "target_z": 2.1250000455755176, "ce": 5.383228778839111, "genuineness": 4.1998209953308105, "identity": 0.5619717836380005, "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/emo_Distress/2f11c3ff647320bffe4cced7493cea68faa69233589ac9906ce756f7bdd241f1.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": "3168cc8472d6146797a2ac070eea6cdcb77c8618ffe7f4ffa62556116c59999a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "479784976741e0a78eb7ee12c6b68b18d26080ba0617ce9bdfbf6929103a17f6", "generation_seconds_batch": 23.407246778020635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783389091491699, "target_z": 2.8437500250665346, "ce": 5.696964263916016, "genuineness": 4.042920112609863, "identity": 0.5498676896095276, "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": 0.03999999999999915, "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/emo_Distress/3168cc8472d6146797a2ac070eea6cdcb77c8618ffe7f4ffa62556116c59999a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "316977efd245072a0a383a0f023db57bd1922d3a8e978012cd486a1c22e3dbe2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5209aa5db1fe13c77316f1a62212903fa0eb942f5e336e39a556362a55e6343a", "generation_seconds_batch": 15.247200058074668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6257708668708801, "target_z": 0.20410157054692737, "ce": 5.744620323181152, "genuineness": 4.344170093536377, "identity": 0.6238824725151062, "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/emo_Distress/316977efd245072a0a383a0f023db57bd1922d3a8e978012cd486a1c22e3dbe2.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": "31d88bae2f84ce48ff5f610d4772410776307ece7cb398f13ec638526d0f9886", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5bfc0b90ead8396e2c9583b4984f5bde9c949d7a533344d1813b86ceb71cfb5", "generation_seconds_batch": 17.035639966954477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6007773876190186, "target_z": 3.843749806304049, "ce": 6.006728172302246, "genuineness": 3.616149425506592, "identity": -0.05506400763988495, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de lijn. En daarna, naast het traam, neem ze mee als je weggaat.", "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/emo_Distress/31d88bae2f84ce48ff5f610d4772410776307ece7cb398f13ec638526d0f9886.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": "32de34b5168340b37db45382e0387ec80efd6228e4e46362a33d95880f81a97a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d6d2821b9a41f74aecda9af06a1f5c51004d556157669c98983546cc0bbf354", "generation_seconds_batch": 16.499845883110538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5571230053901672, "target_z": 0.12011719398026893, "ce": 5.871703147888184, "genuineness": 3.998987913131714, "identity": 0.5398793816566467, "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/emo_Distress/32de34b5168340b37db45382e0387ec80efd6228e4e46362a33d95880f81a97a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "3365a7987fd95a4d62b3335e6f3578eb17e2698e48aa12dcc98490386e3c0512", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7a05276b5763160c220ad693c9bbd1f005f7da11d11efff44fbdc0f02588d4f5", "generation_seconds_batch": 22.499312413972802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 5.240260601043701, "genuineness": 3.6789097785949707, "identity": 0.5650738477706909, "hypothesis": "Encontrado la cajita. Estaba junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/3365a7987fd95a4d62b3335e6f3578eb17e2698e48aa12dcc98490386e3c0512.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "33a3f4b47f942389e4d7497b2a333dce3b023fe6e55abb033abbbb1ceea1674e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "14dc556ac2e87beabfc031db19ed4e073c78609affacc9acc0278b28609d2a66", "generation_seconds_batch": 24.96360229398124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15241992473602295, "target_z": -0.37499999088489644, "ce": 5.982900142669678, "genuineness": 4.2374773025512695, "identity": 0.48447978496551514, "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/emo_Distress/33a3f4b47f942389e4d7497b2a333dce3b023fe6e55abb033abbbb1ceea1674e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "33cb63d8b6c9c774f8f74f2c5694cad13eef413f9b17782ef49a1a1ba8fa8745", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "154465fb3ee50a88c05c944c4418858472a5016a21feec4a48e3cc06c56f318c", "generation_seconds_batch": 15.100431557977572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15241992473602295, "target_z": -0.37499999088489644, "ce": 6.086154937744141, "genuineness": 4.482243061065674, "identity": 0.6132853031158447, "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/emo_Distress/33cb63d8b6c9c774f8f74f2c5694cad13eef413f9b17782ef49a1a1ba8fa8745.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "04f1660a0525d1c5db04353cb0a78f5fe7196c5fcb62807242b857c7758ee594", "generation_seconds_batch": 13.723201034939848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3240395784378052, "target_z": -0.16503904946825038, "ce": 6.1020402908325195, "genuineness": 4.469690799713135, "identity": 0.6915194988250732, "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/emo_Distress/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "53594e15017f3a6999ba937ebb5f8a36e687950a8f267e775e42470bf69b3c97", "generation_seconds_batch": 17.414984659990296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226642370223999, "target_z": -0.28906250284846985, "ce": 6.443574905395508, "genuineness": 3.8797430992126465, "identity": 0.19681979715824127, "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/emo_Distress/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "34abaf8c0936ac3ecd3c55083fef8c6384d07c49d3a88db9f918873ba0702e9e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bbb346f5f029d862c289b32281d47aeed6583725a868166b2a37cc5eb5292911", "generation_seconds_batch": 19.08477616601158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9583849906921387, "target_z": 4.281249984048569, "ce": 5.522225379943848, "genuineness": 3.380797863006592, "identity": 0.5955079793930054, "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/emo_Distress/34abaf8c0936ac3ecd3c55083fef8c6384d07c49d3a88db9f918873ba0702e9e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "34e97f6d15c4090086cf6f4a75283e26719ecd1c52bf16cd09f1f706695026c7", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "951527b35f29434803a866847bf351104afcd3c94eb1b62edefb7548bdca6da0", "generation_seconds_batch": 14.52448257803917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2003137767314911, "target_z": -0.3164062457272952, "ce": 6.133810997009277, "genuineness": 4.532451152801514, "identity": 0.5309786796569824, "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/emo_Distress/34e97f6d15c4090086cf6f4a75283e26719ecd1c52bf16cd09f1f706695026c7.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": "355ba4d29fb8ead1db4372e2b61fe739be8d13bc3cd08d1b31bb1674481a72ec", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d71b95e0bf12ca9c53be6c9265947f73a2cee9207e1fed24f0fc8de14073d3e", "generation_seconds_batch": 17.936565425945446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2176265716552734, "target_z": 3.3749998450432397, "ce": 5.824047088623047, "genuineness": 3.7291181087493896, "identity": 0.30816030502319336, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las het. Twee keer. Legde mijn telefoon weg. Ze hebben zeg maar wanneer we kunnen praten.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/355ba4d29fb8ead1db4372e2b61fe739be8d13bc3cd08d1b31bb1674481a72ec.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "35dff94adff4599352663071b18b9844ff6762579288de3d17e82c47eb8f507e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2e19c074367cb76055cada85224866cdad36a8963290ae6988e2939aec7966d9", "generation_seconds_batch": 20.341323441942222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0771379470825195, "target_z": 3.203124868970386, "ce": 5.7684478759765625, "genuineness": 3.9299514293670654, "identity": 0.15363168716430664, "hypothesis": "De deur staat nog open. Ik heb je ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "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/emo_Distress/35dff94adff4599352663071b18b9844ff6762579288de3d17e82c47eb8f507e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "366dc38895d6faf674875c11e3453d270f612ef212effc0e26e7c8306792208a", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "654cbfaf5cab315c9f8d5868acfdb79ec8c1b3c3b351736ab3f50e337fadb663", "generation_seconds_batch": 16.820383492973633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26018109917640686, "target_z": -0.2431640551651901, "ce": 6.0305562019348145, "genuineness": 4.482243061065674, "identity": 0.3275097608566284, "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/emo_Distress/366dc38895d6faf674875c11e3453d270f612ef212effc0e26e7c8306792208a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "3692d42590b5f679c3721c694e22f8e1e324ff01d7d3d65ec7b8ee9af2e90858", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a374b27c992744f2346f81aebfd7ecbf9dffd30981402b8331423ff40be49e22", "generation_seconds_batch": 22.19792642397806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787722826004028, "target_z": 1.8593749897455085, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.6860246658325195, "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": 0.03999999999999915, "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/emo_Distress/3692d42590b5f679c3721c694e22f8e1e324ff01d7d3d65ec7b8ee9af2e90858.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": "369ad13dc284551561052f29df9afff94fc3db368216fc7ed1b451fbeb1a8bae", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5610d0536635c20291f677544f35d515ab7ee2e121f66e94aab267f1f9ca1ac", "generation_seconds_batch": 22.525880674947985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.639092445373535, "target_z": 3.890624773261799, "ce": 5.6532793045043945, "genuineness": 3.7542223930358887, "identity": -0.16238553822040558, "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/emo_Distress/369ad13dc284551561052f29df9afff94fc3db368216fc7ed1b451fbeb1a8bae.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "36c6bd332f19b1235e968aa4c4c0310d0ab8c40caff51dc201c029d40bfa5515", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "171c00bb5ded53a28e41f67ae81cbe184240dbfa21bd1e31fd10721ee9081c33", "generation_seconds_batch": 21.238182688015513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8676348328590393, "target_z": 0.5, "ce": 5.9431867599487305, "genuineness": 4.482243061065674, "identity": 0.7392898201942444, "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/emo_Distress/36c6bd332f19b1235e968aa4c4c0310d0ab8c40caff51dc201c029d40bfa5515.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "36e99834ef9ddd88fa2997009de07b4e840681f1956a0ee7d0a38d812bbad754", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "851fcf62cf839408654b316e7925a321ead42466877cc12ee8992a5dfdd6abbd", "generation_seconds_batch": 21.238182688015513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5062196254730225, "target_z": 1.2812500569693972, "ce": 5.7406487464904785, "genuineness": 4.356721878051758, "identity": 0.5904098749160767, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la... 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/manual-comparison-v1/audio/emo_Distress/36e99834ef9ddd88fa2997009de07b4e840681f1956a0ee7d0a38d812bbad754.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": "372dc84c17fb8eb3f020035c20223914a5ea7effa1fc5160b0649b619c7d7a47", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbb0b5389bc756bcfc89c8838ccae43880420b8e315c9e305ac7d97a4e52d73b", "generation_seconds_batch": 17.177851804997772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1409964561462402, "target_z": 3.2812499111277402, "ce": 5.974957466125488, "genuineness": 3.961331605911255, "identity": 0.3485298156738281, "hypothesis": "Die Schlüsse 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/emo_Distress/372dc84c17fb8eb3f020035c20223914a5ea7effa1fc5160b0649b619c7d7a47.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "3735ec2e503b9641eb2f9bb45c582cae2fcef208f780c2724c1ef07215d18633", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "677e4f74cb3cdb2f2b15ae442db836b1c68ff80ada06737a39397f7eb22a66e3", "generation_seconds_batch": 22.242864853003994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2529970109462738, "target_z": -0.2519531296999753, "ce": 6.086154937744141, "genuineness": 3.9299514293670654, "identity": 0.49379363656044006, "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/emo_Distress/3735ec2e503b9641eb2f9bb45c582cae2fcef208f780c2724c1ef07215d18633.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "3743bc724536aca882b38dcdb8cf3aacb2edaa930e17a44da6264d2dd4d7acac", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "901ea655e44383e07a57ebbfc3e192c05a6cf79a79b63618e63361711368d72f", "generation_seconds_batch": 17.56610898906365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370887041091919, "target_z": 3.5625000045575517, "ce": 6.022613525390625, "genuineness": 4.344170093536377, "identity": 0.5505202412605286, "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/emo_Distress/3743bc724536aca882b38dcdb8cf3aacb2edaa930e17a44da6264d2dd4d7acac.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "375981a994e1db16dbecae89d8f1a5f266170ada33d1c39fb1c90acb4b594278", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "edef25ed1936da69d4391dc88308a68a72fceef577e09d77a505887a99abb7c6", "generation_seconds_batch": 21.13183899107389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7450737953186035, "target_z": 2.7968747664254714, "ce": 5.561938762664795, "genuineness": 4.20609712600708, "identity": 0.5099146366119385, "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/emo_Distress/375981a994e1db16dbecae89d8f1a5f266170ada33d1c39fb1c90acb4b594278.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "37b9818858c77045234c53c9ce6da1c60bd157725f44b9a88b7ed8e9a45e7162", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "07e0a1069bc454bd7c930c4abc651430a02466d8df7241518173ad0f0fd60bca", "generation_seconds_batch": 15.343514309031889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.125868320465088, "genuineness": 4.846253395080566, "identity": 0.7970046401023865, "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/emo_Distress/37b9818858c77045234c53c9ce6da1c60bd157725f44b9a88b7ed8e9a45e7162.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": "386ed96f42901c814449a2ab14aaa25b798e6cc677375c88ed319a16d2b78dfd", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d450b520e111d09098b7ef40276b80e1a253d25ac91d8b85d9423afba7dc322a", "generation_seconds_batch": 15.085787373012863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7450737953186035, "target_z": 2.7968747664254714, "ce": 5.7128496170043945, "genuineness": 3.986435890197754, "identity": 0.5609868764877319, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Ok, quand tu partiras.", "wer": 0.08333333333333333, "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/emo_Distress/386ed96f42901c814449a2ab14aaa25b798e6cc677375c88ed319a16d2b78dfd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "38920d7a0d81623131adf718d0c4c68e245d59638d979a57ba828e583e4bf302", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5f73e963cae4dd144dbd31ec92cc8f7d7caeed84fe7bc39f137b5b9068e27508", "generation_seconds_batch": 21.10813823796343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226642370223999, "target_z": -0.28906250284846985, "ce": 6.308549880981445, "genuineness": 4.444586753845215, "identity": 0.4987337589263916, "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/emo_Distress/38920d7a0d81623131adf718d0c4c68e245d59638d979a57ba828e583e4bf302.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "38a67cec2c98252d71e365b636c53683b9df0ae236d35c33b89a9f343b36256b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d42a05f178012c07660aa28154cd1c12206d8743dbeeb33cbc44442de91e1f20", "generation_seconds_batch": 21.422422431991436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9749643802642822, "target_z": 3.078124859855283, "ce": 5.919358730316162, "genuineness": 4.356721878051758, "identity": 0.34325408935546875, "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/emo_Distress/38a67cec2c98252d71e365b636c53683b9df0ae236d35c33b89a9f343b36256b.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": "38a8921254df7dc823218adc28a6e0c0b1da0caefd446bb404d0c167be9dc968", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64955bcec09a12f10be5ba2cd8b5fd6966669e33b5a176212dba260bf80d28fd", "generation_seconds_batch": 20.37998330593109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.6532793045043945, "genuineness": 3.9425034523010254, "identity": 0.6707959771156311, "hypothesis": "La carretera y gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te espera. Te esperaré al otro lado.", "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/emo_Distress/38a8921254df7dc823218adc28a6e0c0b1da0caefd446bb404d0c167be9dc968.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "394e6e80d5346d596e5cd7bef5251e175695cefc9fe843edf377d1d7cb2869cf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a8afbc5468725d53624b5089b775e6f31c0508769220f4f080104d06f08086e8", "generation_seconds_batch": 21.67572642909363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.204854965209961, "target_z": 3.3593749532850943, "ce": 5.609594821929932, "genuineness": 4.18099308013916, "identity": 0.5351893901824951, "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/emo_Distress/394e6e80d5346d596e5cd7bef5251e175695cefc9fe843edf377d1d7cb2869cf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "39676f0f9cb71c6689020ad56f17307809c1662f08424e72b70a403c4843daf7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "711fd1cc0f9fcc2185c7920635da20285b4037840d69d7ff3821a02e4db13254", "generation_seconds_batch": 19.89310020301491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29610148072242737, "target_z": -0.19921875541209275, "ce": 5.982900142669678, "genuineness": 3.8295347690582275, "identity": 0.5331050157546997, "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/emo_Distress/39676f0f9cb71c6689020ad56f17307809c1662f08424e72b70a403c4843daf7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "396daaa0aa2530ffa6fa50e31b60ec6ac1652cbeaf9d0e872cd61b2dc46cd42f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a387d0889af48250206ffe4eb5b3fc7eba4f8c17e2d4f36d4924710e25e61d92", "generation_seconds_batch": 16.408251077053137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.757845640182495, "target_z": 2.8124999498669303, "ce": 5.847874641418457, "genuineness": 4.15588903427124, "identity": 0.5409494638442993, "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/emo_Distress/396daaa0aa2530ffa6fa50e31b60ec6ac1652cbeaf9d0e872cd61b2dc46cd42f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "39b04d1207cbc2b4abdd3b54fd3d79d5cccce52e4ec6ffc0b6252308f6424cb5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d6f325fb0115b1124552c83f635e0e47409ee7df2eac195861872e80058e421d", "generation_seconds_batch": 22.19792642397806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.119260787963867, "target_z": 2.0312498199767046, "ce": 6.308549880981445, "genuineness": 4.18099308013916, "identity": 0.5306902527809143, "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": 0.03999999999999915, "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/emo_Distress/39b04d1207cbc2b4abdd3b54fd3d79d5cccce52e4ec6ffc0b6252308f6424cb5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "39f7e695e1f4676791d5f2044d718501651ea53b998e895721271f4f284b5ee8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c878be4953fd2681e28c57e1e133283c804fe64cb4c640a62d1859269f039167", "generation_seconds_batch": 21.877632772899233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370887041091919, "target_z": 3.5625000045575517, "ce": 5.704906940460205, "genuineness": 3.7793264389038086, "identity": 0.30790773034095764, "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/emo_Distress/39f7e695e1f4676791d5f2044d718501651ea53b998e895721271f4f284b5ee8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "3a75ffe621ded887ce4e365c5ee258af1d9a36d887d1adae4379f192839a6e5c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4c2ec780513d9e46c9e7bc889cfaa5bfa8cbc20d9f65f400fdb0760ae85c6023", "generation_seconds_batch": 22.499312413972802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9621927738189697, "target_z": 3.0624999680971374, "ce": 5.422942161560059, "genuineness": 3.6475296020507812, "identity": 0.5326230525970459, "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/emo_Distress/3a75ffe621ded887ce4e365c5ee258af1d9a36d887d1adae4379f192839a6e5c.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": "3ad811ae96affbec62a6c6eb6aea7dcaa45705d2c9a94def69e08906c2096cb9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5618e17509583d4635016969d800e0d82c8a51d7ccbdc3ec3411b50e33d49487", "generation_seconds_batch": 18.288125770981424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4168176651000977, "target_z": 1.1718749396124388, "ce": 6.0146708488464355, "genuineness": 4.218649387359619, "identity": 0.42519235610961914, "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/emo_Distress/3ad811ae96affbec62a6c6eb6aea7dcaa45705d2c9a94def69e08906c2096cb9.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": "3ade8405257621ab4e6b41bc2ac42e629fa3e51b33255c555b85da1b08a58670", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1bdf2dc9117e9a463761c9d0fc57f19cfe3687bb6122d08c4c159d8d4bee31a", "generation_seconds_batch": 17.04333790903911, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6301286220550537, "target_z": 2.6562498655522226, "ce": 5.486483573913574, "genuineness": 3.625563621520996, "identity": 0.2888038754463196, "hypothesis": "De weg gaat linksaf naar de brug. Lop verder. Tot aan het kleine houten. Ik wacht en dan aan de andere kant.", "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/emo_Distress/3ade8405257621ab4e6b41bc2ac42e629fa3e51b33255c555b85da1b08a58670.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": "3b21602489a142470559c0131b23e53015230585601b894c8fd2f3fbac10e90e", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3ce5ecc7eb62a617d8f402506a96acd048d3cce5dffe08ccd1479d25e7e07cb", "generation_seconds_batch": 17.708016292075627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.349151372909546, "target_z": 2.312499913406516, "ce": 5.510311126708984, "genuineness": 4.055472373962402, "identity": 0.479110985994339, "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/emo_Distress/3b21602489a142470559c0131b23e53015230585601b894c8fd2f3fbac10e90e.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "d4f34b66b1f76a04ab6c66149e047aa1c636d05b99b70e824715218867b7f8ab", "generation_seconds_batch": 13.708990516955964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16838452219963074, "target_z": -0.35546876680597217, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.5453071594238281, "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/emo_Distress/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "3c5c695cdd4fb225f3fcd4e3d2cf7c6976ce2346e1af1ded44896b3f4aad31c6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c4281fd6de988fbd5ed3f523344b2a6f2d208c26b4f258cc9419415379aecb3f", "generation_seconds_batch": 22.686903933994472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5220008492469788, "target_z": 0.07714844996205565, "ce": 5.903473377227783, "genuineness": 4.231201171875, "identity": 0.65850830078125, "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/emo_Distress/3c5c695cdd4fb225f3fcd4e3d2cf7c6976ce2346e1af1ded44896b3f4aad31c6.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": "3c639f490a34a67eebbeb562771b936fab9b0ca8ca48c162dd80f247ddad3a22", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2eedbff43797d35f7757ba84ffcd5c3729f19bce0355f57a215bd846f81caaf3", "generation_seconds_batch": 17.936565425945446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5496907234191895, "target_z": 3.7812499475881545, "ce": 5.792276382446289, "genuineness": 3.7291181087493896, "identity": 0.46589380502700806, "hypothesis": "Ik ben erg prachtig kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weer. Zeg maar wanneer we kunnen praten.", "wer": 0.21739130434782608, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/3c639f490a34a67eebbeb562771b936fab9b0ca8ca48c162dd80f247ddad3a22.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "3c646c219b58285c1ac072f259e605502f8f77bd2d2568004fead2ddee79b010", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "61d25d421be521296404cd6db6b0d88f5e06a64a3bca3191b45ec593feea85fc", "generation_seconds_batch": 21.371548107941635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3363797664642334, "target_z": 2.296875021648371, "ce": 5.80021858215332, "genuineness": 4.218649387359619, "identity": 0.376512736082077, "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/emo_Distress/3c646c219b58285c1ac072f259e605502f8f77bd2d2568004fead2ddee79b010.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "3cdbb71a0cbf27107f47ea13cc5c410cb092b1072c09645d2dabb23b2742bc8a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ed6d52582c3900b43bac1567ff32f8334fde0c36102f9d789561e4928529b558", "generation_seconds_batch": 23.538451493019238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6914092302322388, "target_z": 1.5078125917207295, "ce": 5.927301406860352, "genuineness": 4.406930446624756, "identity": 0.6845424771308899, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/3cdbb71a0cbf27107f47ea13cc5c410cb092b1072c09645d2dabb23b2742bc8a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "3cf36aad5296aa881b7eddc5f13aa3fff6847cd45dd9a15602a00bae3fa2ae7c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0f1cb6227c2b70fa8d240795b630301aae6dedde5888a44dadc7570804c144e3", "generation_seconds_batch": 14.539664278039709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4602887630462646, "target_z": 3.671874830231196, "ce": 5.911416053771973, "genuineness": 3.9048471450805664, "identity": 0.3084564507007599, "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/emo_Distress/3cf36aad5296aa881b7eddc5f13aa3fff6847cd45dd9a15602a00bae3fa2ae7c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "3d23d91838725b65a7834235b1a2e60b0a8becb349d83b5f40f35e09ff9bddd5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cdeb5b5e5d970a7dbb9b72aaf16efb3e20268e7adad8948dcdd95f2624f0e742", "generation_seconds_batch": 22.080132103990763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.627550721168518, "target_z": 1.4296875495633756, "ce": 6.292664527893066, "genuineness": 3.7918784618377686, "identity": 0.5001587867736816, "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/emo_Distress/3d23d91838725b65a7834235b1a2e60b0a8becb349d83b5f40f35e09ff9bddd5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "3da124733ab8a51ec2034426b6af438492c854b661d6309ec67c8843874181a5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7f5800e68520e60c644be60849c856c87427fec483fb524577b994816f8d7fe7", "generation_seconds_batch": 15.97321290790569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8600192070007324, "target_z": 2.937499958982034, "ce": 5.855817794799805, "genuineness": 4.093128204345703, "identity": 0.6867188215255737, "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/emo_Distress/3da124733ab8a51ec2034426b6af438492c854b661d6309ec67c8843874181a5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "3db3ae922862bfb95af72a2a0afefd75b8d7ad4697c379f0f2995486bb2aeaea", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "33ad2b2aa00bb31e4bd6896a226100d666d9709dec1b26db0b0a5dd10c01e89f", "generation_seconds_batch": 20.749186484958045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22585716843605042, "target_z": -0.2851562434485193, "ce": 6.348263263702393, "genuineness": 4.519899368286133, "identity": 0.4488821029663086, "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/emo_Distress/3db3ae922862bfb95af72a2a0afefd75b8d7ad4697c379f0f2995486bb2aeaea.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "3dd14ba06abf3aa1682c00157055bcd21578465fa16b714f08b86fdb409a63b3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f06a7389139aa4903e4c68cbc8b5d63119f732310481ea2cd967f17ba35bf29", "generation_seconds_batch": 20.67262819199823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1166828870773315, "target_z": 0.8046875039878578, "ce": 5.998785495758057, "genuineness": 4.406930446624756, "identity": 0.6941276788711548, "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/emo_Distress/3dd14ba06abf3aa1682c00157055bcd21578465fa16b714f08b86fdb409a63b3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "3ddbd00659e0682d08f1b304a081653752657c0cd028c8fded6039a26dedf5a4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "356076a0adcb705db4e0e10fe379fb808713d66d247e13881cda76e137c0013f", "generation_seconds_batch": 22.589896689984016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18754208087921143, "target_z": -0.33203124686668317, "ce": 6.181467056274414, "genuineness": 4.808597087860107, "identity": 0.5988147258758545, "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/emo_Distress/3ddbd00659e0682d08f1b304a081653752657c0cd028c8fded6039a26dedf5a4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "3ddc497ba408d24345c36cad877fd59453c9a8e76c2a609925c1fb99c39a241b", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "50964c843daa335176ed3b6bbce355305c33a89530d28451ef5f42991a93c2d2", "generation_seconds_batch": 14.977032487047836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06780743598937988, "target_z": -0.47851562799089337, "ce": 6.403861999511719, "genuineness": 4.545003414154053, "identity": 0.6211382746696472, "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/emo_Distress/3ddc497ba408d24345c36cad877fd59453c9a8e76c2a609925c1fb99c39a241b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "3e106d7fb342da009c5646f2409690d0c3c1d2657bb1b7ac342da1e0ca1371e0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0aa491eed4411330097b0f8aa4c53ba217199eb50ae9ae92e69a3f77249a5dc5", "generation_seconds_batch": 20.564955975976773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3401875495910645, "target_z": 1.0781250056969398, "ce": 6.181467056274414, "genuineness": 4.3127899169921875, "identity": 0.5951474905014038, "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": 0.03999999999999915, "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/emo_Distress/3e106d7fb342da009c5646f2409690d0c3c1d2657bb1b7ac342da1e0ca1371e0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "3e43713d4a120fba044609c7eb4e2279b3e3433607082d4e5e48766b6c9d2d44", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f34314dfbacef36f06443caa28e57731b9c7a6983f34124e360f704e7098ff40", "generation_seconds_batch": 22.686903933994472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9793871641159058, "target_z": 0.636718750854541, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.7182501554489136, "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/emo_Distress/3e43713d4a120fba044609c7eb4e2279b3e3433607082d4e5e48766b6c9d2d44.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": "3e56cc0625f16bf1ee851235d5c439ea56ed5fa4f997133efa6a2df1f3d3974b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bae582db04aecd3c0943ae15acd3bdde5c70f8221557a88e1a1b921e0e5df366", "generation_seconds_batch": 21.636190418037586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6901793479919434, "target_z": 3.9531249236610075, "ce": 5.847874641418457, "genuineness": 3.5220088958740234, "identity": 0.586094081401825, "hypothesis": "La carretera irá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "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/emo_Distress/3e56cc0625f16bf1ee851235d5c439ea56ed5fa4f997133efa6a2df1f3d3974b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "3e69b6277f0c7c832a17c399b0204f46cadde0169bb9397bee17e5bc989ec5dd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1609c33454ea7a8ec667fb123a4b1569c90131e99281b209be986004b2d1cb43", "generation_seconds_batch": 17.81304517108947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2469778060913086, "target_z": 2.1874999042914127, "ce": 6.117925643920898, "genuineness": 4.394378662109375, "identity": 0.5009926557540894, "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/emo_Distress/3e69b6277f0c7c832a17c399b0204f46cadde0169bb9397bee17e5bc989ec5dd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "3ecf122b1ef30cc3c23bc1d1ad56fe695c1e89a53f65d981623a48d7742e6f0f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3c31535a9e9c3b6ac283f7a471176e340b64a39ada69d9c01f25d7a65f862b7b", "generation_seconds_batch": 24.36039050796535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5427548289299011, "target_z": 0.1025390449106986, "ce": 5.9431867599487305, "genuineness": 4.149612903594971, "identity": 0.7743273973464966, "hypothesis": "De deur staat nog open. Ik heb je jas op 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/emo_Distress/3ecf122b1ef30cc3c23bc1d1ad56fe695c1e89a53f65d981623a48d7742e6f0f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "3ee05dd26c38810c744a33aad396c15d8d05844568fbb13ee8ea1014e33d6011", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "fed2cbd6f0df7048e0c9c74679d067a36d708a644c1d1a482a4da242e18c7079", "generation_seconds_batch": 16.244832136901096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.898334264755249, "target_z": 2.9843749259397834, "ce": 5.649308204650879, "genuineness": 3.9801597595214844, "identity": 0.14978700876235962, "hypothesis": "De deur staat nog open. Ik heb je jas op de jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/3ee05dd26c38810c744a33aad396c15d8d05844568fbb13ee8ea1014e33d6011.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "3f574037269043a4c616d19f258f3ad502a9a9562466605abc42c6472c55cf13", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "194c35e3bb37ba250702d4e1682b7209dc34f997aa2d98a5b74983bad6f6f085", "generation_seconds_batch": 16.36108341498766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7910046577453613, "target_z": 0.40624999316367233, "ce": 5.855817794799805, "genuineness": 4.607763767242432, "identity": 0.5500460863113403, "hypothesis": "J'ai trouvé la petite boîte. Elle était elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/3f574037269043a4c616d19f258f3ad502a9a9562466605abc42c6472c55cf13.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": "3f867cf662f16347caf4ddc81311f521f64d3ed517d7f65f27cc0ab1a154cca1", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "83cb29f163d3030b36f7fec0063501df8b179f02d12c31f1f3222d0e4e482ce5", "generation_seconds_batch": 22.15724755206611, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4423611164093018, "target_z": 1.2031250148120434, "ce": 5.839932441711426, "genuineness": 3.600459337234497, "identity": 0.37073665857315063, "hypothesis": "Ik schreef nummer op de envelop, lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "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/emo_Distress/3f867cf662f16347caf4ddc81311f521f64d3ed517d7f65f27cc0ab1a154cca1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "3fd662037fc46f2867975536033a6b595a5f87ccdde684841f0d49fd495f83e4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5eb3a28ae26d2ca6d31eb55ce6b67d61e57b0e50040976beed10d9ec29ba2e1e", "generation_seconds_batch": 24.417777566006407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14443761110305786, "target_z": -0.3847656211545657, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.5782567262649536, "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/emo_Distress/3fd662037fc46f2867975536033a6b595a5f87ccdde684841f0d49fd495f83e4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "40101730094bd8c8f6968386c3590c600c4ad7dafc4c4099242179d2e8fd8059", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "83d6b355266483f9c4ba40252dd971ded122c696cbeb9ae5757d7f0c13d40936", "generation_seconds_batch": 23.21059801708907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3274158239364624, "target_z": 1.0624999680971376, "ce": 6.252951145172119, "genuineness": 4.293961524963379, "identity": 0.6453559398651123, "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/emo_Distress/40101730094bd8c8f6968386c3590c600c4ad7dafc4c4099242179d2e8fd8059.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "40578e8d75c108239cb7b0029534c00311ef4b054c2a9c28d920a91bca50251d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d05476a4036f5b8cd4dc4c7dc173c02d939075299c6a4fc25d34ea9cc66a752f", "generation_seconds_batch": 23.171015249099582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42780959606170654, "target_z": -0.03808592888337867, "ce": 5.911416053771973, "genuineness": 4.381826400756836, "identity": 0.5265721678733826, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Tot is even onbewit aan het vuil.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/40578e8d75c108239cb7b0029534c00311ef4b054c2a9c28d920a91bca50251d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "40a31a3661379abf2e4d8e0566306e68fc92fdf308799e3932adad1ef51d2446", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f65837406e7bf39fcfe84a0727bcc3b6faca050814947543c9a8db25a4cd405e", "generation_seconds_batch": 17.425187162007205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.447517156600952, "target_z": 3.656249938473051, "ce": 5.5817952156066895, "genuineness": 4.011539936065674, "identity": 0.7179317474365234, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.3684210526315789, "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/emo_Distress/40a31a3661379abf2e4d8e0566306e68fc92fdf308799e3932adad1ef51d2446.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "4107802a5fdc78a43260169e537b0255d27aa4d9f1ea0154c27c1b3e04b1f31a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6eaf82f3fa381987e270d538d74d3974aa54724a1d8921571d0924669a5a32c2", "generation_seconds_batch": 16.425440062070265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.685023307800293, "target_z": 1.5, "ce": 5.919358730316162, "genuineness": 3.848362922668457, "identity": 0.2612841725349426, "hypothesis": "I found the little box. It was beside the old Wait. 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/emo_Distress/4107802a5fdc78a43260169e537b0255d27aa4d9f1ea0154c27c1b3e04b1f31a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "413b4c4a43386ef2014eeac06aa8da69fbefad72e01fe964076620fd2a8c94c6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2ac4b333153bc43b23d1cf963c2a80323b8d8c21cfd7da71a306e10147818aa8", "generation_seconds_batch": 22.530892045935616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.064366340637207, "target_z": 3.187499977212241, "ce": 5.95112943649292, "genuineness": 4.017816066741943, "identity": 0.6826597452163696, "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/emo_Distress/413b4c4a43386ef2014eeac06aa8da69fbefad72e01fe964076620fd2a8c94c6.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": "4189cb26f72bddc81776a28f78d00a710bfef2a11123ec2eac64dfebf42b9816", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7455042198ac1010e2a58bb2f2a0660f77b4fcedfb14665c26f8730be87ffadd", "generation_seconds_batch": 17.264412602060474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.754037857055664, "target_z": 4.031249965818362, "ce": 6.038498878479004, "genuineness": 3.575355052947998, "identity": 0.5481438636779785, "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/emo_Distress/4189cb26f72bddc81776a28f78d00a710bfef2a11123ec2eac64dfebf42b9816.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "41c38eaa7c91e51b1fd138b795dea71f0424c4dc030586f54f0ad7eb6bad5df9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c211cca348de82dcb9298afa4642e3e8298f587d33b425ccfcc4200146c32894", "generation_seconds_batch": 15.733237804030068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4602887630462646, "target_z": 3.671874830231196, "ce": 5.319687366485596, "genuineness": 3.8546390533447266, "identity": 0.6944852471351624, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 0.3888888888888889, "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/emo_Distress/41c38eaa7c91e51b1fd138b795dea71f0424c4dc030586f54f0ad7eb6bad5df9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "41e74c4a22e73f82e0d9567f189bfc6d0c6e18683b0002f47f82930b7cf29030", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3d5650cbce9062759e98730bf5ef3f81d204056f0990041811a4e1d792103c20", "generation_seconds_batch": 22.510182866011746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.115453004837036, "target_z": 3.249999835928136, "ce": 5.831989288330078, "genuineness": 4.042920112609863, "identity": 0.5585868954658508, "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/emo_Distress/41e74c4a22e73f82e0d9567f189bfc6d0c6e18683b0002f47f82930b7cf29030.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "41faf347c03af33c0f299bf4e449e0e3b2d1496529967b0a95fd0aff31f1af25", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bb77393a8d260665735c37741917c2be804335fdab9c17f33564e7be691c743b", "generation_seconds_batch": 25.23160865297541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1731739342212677, "target_z": -0.34960935947583927, "ce": 6.0305562019348145, "genuineness": 4.7332844734191895, "identity": 0.7292562127113342, "hypothesis": "J'ai trouvé la petite boîte elle était près de la de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/41faf347c03af33c0f299bf4e449e0e3b2d1496529967b0a95fd0aff31f1af25.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "425d91b05c25b362491e0251e55c86cc60333aa92477411949c365857e07e755", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2c7a1ab86b8b22495989f22595006e4707b68a44f49046ee79ea87a61ed5a654", "generation_seconds_batch": 16.6314869140042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.132032632827759, "target_z": 2.046875003418164, "ce": 6.157639026641846, "genuineness": 4.105680465698242, "identity": 0.4150388538837433, "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/emo_Distress/425d91b05c25b362491e0251e55c86cc60333aa92477411949c365857e07e755.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "42c1ea6fa5bce7fa45199a708d1b28499cfe49e588907a42ef36c56c4a907cfe", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2e72d89caa2d4439e2c7fcdd982b4f0abf65519ed94a94a4c2e7035ee0f60494", "generation_seconds_batch": 19.430499386042356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1358404159545898, "target_z": 0.8281249874667326, "ce": 5.974957466125488, "genuineness": 4.7834930419921875, "identity": 0.7626956701278687, "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/emo_Distress/42c1ea6fa5bce7fa45199a708d1b28499cfe49e588907a42ef36c56c4a907cfe.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "214cbddb1bc88249cfc4d0ab87655178db3695c351462df7078a4b136054e29a", "generation_seconds_batch": 13.723201034939848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1588057577610016, "target_z": -0.3671875085454096, "ce": 6.09409761428833, "genuineness": 4.337893962860107, "identity": 0.7753071188926697, "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/emo_Distress/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "43b036409ac9db54c7f5f5f98a4ddd791a48da11f7ae88b5c4ec7d6c030d7a3a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "262c9f342a961f92d482b0ce3b9e0e03ba7ca89a8f2f2aacd24984bca5b1e2b4", "generation_seconds_batch": 22.225379720097408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.923877716064453, "target_z": 3.015625001139388, "ce": 5.855817794799805, "genuineness": 4.168440818786621, "identity": -0.0032184235751628876, "hypothesis": "De deuren staan nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "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/emo_Distress/43b036409ac9db54c7f5f5f98a4ddd791a48da11f7ae88b5c4ec7d6c030d7a3a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "43b7787b84b30fab676ac3bee400c28b7f03770cb117c6920843fc33dafee27e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4016f88fa1295226a1ac698bb25ead6a8b61067061e3271d7c0b33c9984d96f0", "generation_seconds_batch": 21.942727606045082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40545913577079773, "target_z": -0.06542967176220402, "ce": 6.221180438995361, "genuineness": 4.3127899169921875, "identity": 0.5883378386497498, "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/emo_Distress/43b7787b84b30fab676ac3bee400c28b7f03770cb117c6920843fc33dafee27e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "43d253d5ed824591b24d88aaaf9969c91b765ad6165a42ce067ed4d90136f486", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "15e06eaeb79c7b78b4dd872ae44e6265ad83778531d10305c298e23c44b54896", "generation_seconds_batch": 23.159329804009758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5036415457725525, "target_z": 0.05468752221806492, "ce": 6.117925643920898, "genuineness": 4.7458367347717285, "identity": 0.6177475452423096, "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/emo_Distress/43d253d5ed824591b24d88aaaf9969c91b765ad6165a42ce067ed4d90136f486.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "44f2ca419923fad7ccb943200dc51af22335ce42cfd1fab257040cf34c780de5", "generation_seconds_batch": 16.843687422922812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1651916205883026, "target_z": -0.3593749897455085, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.6008350849151611, "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/emo_Distress/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "44397295f0e0bf57994548569f85331f6c187cf9f98517dc7c395db824e57994", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d0c9a0826f27086b7901b9bc90103f1539a230d8ac4e3574481bbe2b597e9801", "generation_seconds_batch": 16.581631037057377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.462133526802063, "target_z": 0.003906259399950545, "ce": 6.125868320465088, "genuineness": 4.3127899169921875, "identity": 0.7301300764083862, "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/emo_Distress/44397295f0e0bf57994548569f85331f6c187cf9f98517dc7c395db824e57994.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "44ac60f0636f91b4218fafe76fe59da9a6e64cc8247385736cfc3e604e2a639b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a3bb39079d4b1b35d136937db509909bd1996028de47b9e73b65841f163bddf7", "generation_seconds_batch": 22.091165601974353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14124467968940735, "target_z": -0.38867188055451624, "ce": 5.7684478759765625, "genuineness": 4.21237325668335, "identity": 0.5482231378555298, "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/emo_Distress/44ac60f0636f91b4218fafe76fe59da9a6e64cc8247385736cfc3e604e2a639b.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": "44dc12207af09dd70348f224c44db48794cb242c59412d4eaa36c03b5657daae", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c4c6f3126cfff18dd4f87cecac2244c8500b8bf58b7cb5c325217d3c600ca424", "generation_seconds_batch": 16.860703871003352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.757845640182495, "target_z": 2.8124999498669303, "ce": 5.959072113037109, "genuineness": 4.20609712600708, "identity": 0.6491765975952148, "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/emo_Distress/44dc12207af09dd70348f224c44db48794cb242c59412d4eaa36c03b5657daae.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "456893aa4b2d2730a63fe466f2d8688029698c36fe36dbe5634394b826243fd7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f83f96092403171620daea3d79f0e91c23fec14a37d82f5b4b684d8bd768c34a", "generation_seconds_batch": 14.131936536054127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1007182598114014, "target_z": 0.7851562434485193, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.45294180512428284, "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/emo_Distress/456893aa4b2d2730a63fe466f2d8688029698c36fe36dbe5634394b826243fd7.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": "458e532682b7284cd60c40b03ada38bd923d5c258cfb8f7f0bbfa772c645b2e0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adf36d74778fd31fef25b560cf9c02e9eec24a6346bde642721e95fc4b9ef760", "generation_seconds_batch": 23.60451910609845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.538110733032227, "genuineness": 3.6663577556610107, "identity": 0.5309854745864868, "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/emo_Distress/458e532682b7284cd60c40b03ada38bd923d5c258cfb8f7f0bbfa772c645b2e0.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": "45be0cb122479fd39f1b52a64c2ee6d96fbfd3610fa868ed04c0de3f573a76e1", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03af3f5ffa3c6187c45b6a765e9c987a429d89dcb180f6dbbdd9f55b9ac4d319", "generation_seconds_batch": 16.45169405604247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9314932823181152, "target_z": 0.5781249692365255, "ce": 6.054384231567383, "genuineness": 3.9299514293670654, "identity": 0.5155911445617676, "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/emo_Distress/45be0cb122479fd39f1b52a64c2ee6d96fbfd3610fa868ed04c0de3f573a76e1.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "0813bdb34bc3cba437ed1d2c76a7e9d974336834d651a68e27c4a19e3f15de8a", "generation_seconds_batch": 17.89608310488984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10771897435188293, "target_z": -0.4296875131029614, "ce": 6.332377910614014, "genuineness": 4.162164688110352, "identity": 0.5067603588104248, "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/emo_Distress/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "469036498639729c444dff7fcfc529f4ac7b30e092c56e50c176bd1012ba1eda", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5595276cc625d71b6f47d5e6b7efd6cf876325c71d0d9e6c7d669e92a1a425f5", "generation_seconds_batch": 16.63374863297213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5172114372253418, "target_z": 0.0712890426319227, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.5591925382614136, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/469036498639729c444dff7fcfc529f4ac7b30e092c56e50c176bd1012ba1eda.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "469e9cc06cd3a8c5047f1caa997125a0a51b5941c11bc95f4f4ac0e1a217210d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "15dce2c50a7d38dd2dc69b21b29a6c49f98c9b8b0cc9130889d30b2bc526f26c", "generation_seconds_batch": 22.591464730910957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3581151962280273, "target_z": 3.5468748211160928, "ce": 5.871703147888184, "genuineness": 4.068024158477783, "identity": 0.6087368726730347, "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/emo_Distress/469e9cc06cd3a8c5047f1caa997125a0a51b5941c11bc95f4f4ac0e1a217210d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "4718cb007a306bacaead56865ae061219ea0cb5a7653243ce2f20a0ef798e212", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e80b3533824998af416895f925138ee24bddf7394b62d35464304fab29f53895", "generation_seconds_batch": 21.06169925199356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0554025173187256, "target_z": 1.9531250695026647, "ce": 5.935244083404541, "genuineness": 4.356721878051758, "identity": 0.17408448457717896, "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/emo_Distress/4718cb007a306bacaead56865ae061219ea0cb5a7653243ce2f20a0ef798e212.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "4749fedb9e355a3a7efae7615f6401e9e19a97d1c539a7b33b915ea62c3fc383", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "fd1ba273de3d086246cf4c9797c102dbf8ed20923d01f2803dbc9da2fd6f1b80", "generation_seconds_batch": 16.425440062070265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.365730881690979, "target_z": 1.1093749350548872, "ce": 5.831989288330078, "genuineness": 4.005263805389404, "identity": 0.23941606283187866, "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/emo_Distress/4749fedb9e355a3a7efae7615f6401e9e19a97d1c539a7b33b915ea62c3fc383.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": "47c2247a81388b817ad03db7a8f10c94b54f242cd1f167a36adc948bcf4cd56c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bba93596b5f98d1166bb3a2bc0f816b141ac6ed7e9181918dda7afe4f2ec7f3a", "generation_seconds_batch": 16.45169405604247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38071396946907043, "target_z": -0.09570311830609582, "ce": 6.006728172302246, "genuineness": 4.281409740447998, "identity": 0.5961838960647583, "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/emo_Distress/47c2247a81388b817ad03db7a8f10c94b54f242cd1f167a36adc948bcf4cd56c.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "3070d32811ae96efbef87d3fb2b006f8a99eb3bcd659918fcd7a106b1443052d", "generation_seconds_batch": 16.858448659069836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2577863931655884, "target_z": -0.24609375883025658, "ce": 6.260893821716309, "genuineness": 4.7081804275512695, "identity": 0.7857556343078613, "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/emo_Distress/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "48020dd941130d516dd5d39facfbcaf08c97b17d22f33d2f42a3242db65f6f49", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "786899f534452eab8a4a037ccb9f142bca14ba5a8b2d636b5c0d38a23fcc048c", "generation_seconds_batch": 21.05562697898131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.657250881195068, "genuineness": 4.093128204345703, "identity": 0.4547157287597656, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann leg dich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/48020dd941130d516dd5d39facfbcaf08c97b17d22f33d2f42a3242db65f6f49.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "481fa60a54623f3cd41cd81b4e5de6cf1a0a2eceb92d4004c8ce1072dcde3c0f", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "594b1439fb28b39aa1ef92c29f4269834d4240ee5fddb399a87493c7c7659ddf", "generation_seconds_batch": 15.5343606879469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.046441555023193, "genuineness": 4.7081804275512695, "identity": 0.7659435272216797, "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/emo_Distress/481fa60a54623f3cd41cd81b4e5de6cf1a0a2eceb92d4004c8ce1072dcde3c0f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "4867be380cc019ec8285c7a72e7b7083b2ba480d6782de7071b1d9d850abcdc7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "23a5d57365fec417bbfccfeb84b05294d2e2499f21c0bb937985618d5204e632", "generation_seconds_batch": 21.368085636990145, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4896399974823, "target_z": 2.484374889479369, "ce": 5.609594821929932, "genuineness": 4.168440818786621, "identity": 0.593287467956543, "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/emo_Distress/4867be380cc019ec8285c7a72e7b7083b2ba480d6782de7071b1d9d850abcdc7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "48a384acca17034eabe9ff7f87a6e5699518be5e06e005ae286f4115cfcc0f15", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a52236e188ee995aaf0690ae6a8e7ff4af067a16a1035edd1633951e0340373e", "generation_seconds_batch": 15.63424456503708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3184519410133362, "target_z": -0.1718750125332674, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.46303749084472656, "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": 0.03999999999999915, "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/emo_Distress/48a384acca17034eabe9ff7f87a6e5699518be5e06e005ae286f4115cfcc0f15.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "48ac8e274907717bcd4a38b53410708f26870313e573acfc95764523d7be6b63", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8ceb23d92f810373f9c4a267073a4896197d79bcfc1526f9f8dd4b2b36c63fd8", "generation_seconds_batch": 16.00180724496022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4270113706588745, "target_z": -0.03906248461826274, "ce": 6.086154937744141, "genuineness": 4.65797233581543, "identity": 0.5576663017272949, "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/emo_Distress/48ac8e274907717bcd4a38b53410708f26870313e573acfc95764523d7be6b63.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "4933d8aab1888c40b1d38188c3967c649aff256983b955014b9aae4110dfa9ee", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3b94f82f6cea89e1dba3664068445b757c9b9462c6c69e3043653c96af5c19a2", "generation_seconds_batch": 16.892990329070017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0005078315734863, "target_z": 3.109374935054887, "ce": 5.863759994506836, "genuineness": 4.168440818786621, "identity": 0.194825679063797, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Uh.", "wer": 0.05263157894736842, "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/emo_Distress/4933d8aab1888c40b1d38188c3967c649aff256983b955014b9aae4110dfa9ee.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "49387c9fc10d19f5f8554880178913d671adb7ee7a748a37614c002db4a6b12b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "19ccc72a4707671456ad582832c2a1a018aeef98502fbfafeba2bca3b4046fa1", "generation_seconds_batch": 21.146292528952472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7894082069396973, "target_z": 0.40429688169390415, "ce": 5.863759994506836, "genuineness": 4.7458367347717285, "identity": 0.6254398822784424, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand.", "wer": 0.16666666666666666, "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/emo_Distress/49387c9fc10d19f5f8554880178913d671adb7ee7a748a37614c002db4a6b12b.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "719a5e9cffdf509fc0d4d3dc1d0f30d0742780d68529df5b6e5a97a0c9678541", "generation_seconds_batch": 16.580585776944645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 6.109982967376709, "genuineness": 4.068024158477783, "identity": 0.5279592275619507, "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/emo_Distress/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "49dcef4b131c9fb9f5dba3990d8ac85cea562ded82ed8473edd71e2b27954f0b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d44a40a91934b7dc1227fb05d941f9787e8312a979eabf806bde2b4e2b254ece", "generation_seconds_batch": 21.626170224044472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5241472721099854, "target_z": 3.74999987238855, "ce": 5.6413655281066895, "genuineness": 3.9173994064331055, "identity": 0.6556777954101562, "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/emo_Distress/49dcef4b131c9fb9f5dba3990d8ac85cea562ded82ed8473edd71e2b27954f0b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "4a5c27f8e4f8ccbc782caff15f6e4f9cdb852855547a5f849c7d9e2b5d6072d3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b19996af32c5ef76acc2de5a239c6c03dc94d4922028ed65860a2950f32af3ee", "generation_seconds_batch": 21.75186994089745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9723864793777466, "target_z": 1.8515625438664358, "ce": 5.355429172515869, "genuineness": 4.231201171875, "identity": 0.4456944763660431, "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/emo_Distress/4a5c27f8e4f8ccbc782caff15f6e4f9cdb852855547a5f849c7d9e2b5d6072d3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "4a6d466e0e71e152d4d23068e3283a3d4062af9455fecfc31d5b734ed25e2b82", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "82000753c6aa1a18920361a4415a44c3ac28219c6fd23cc4817fd4c14b9ca523", "generation_seconds_batch": 23.988783151027746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27854040265083313, "target_z": -0.22070312742119938, "ce": 6.229123115539551, "genuineness": 4.21237325668335, "identity": 0.23766911029815674, "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/emo_Distress/4a6d466e0e71e152d4d23068e3283a3d4062af9455fecfc31d5b734ed25e2b82.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "4a9ba04dd9916abedf0470fd3893973329e9da736593a0789e84ab8e853acd77", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7b5309a37271a6fb7d08d8053dbf37df1c605bc509c33c9c8a13f7a3ce53869e", "generation_seconds_batch": 23.218091547023505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7616535425186157, "target_z": 1.5937500797571562, "ce": 6.221180438995361, "genuineness": 4.218649387359619, "identity": 0.34541821479797363, "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/emo_Distress/4a9ba04dd9916abedf0470fd3893973329e9da736593a0789e84ab8e853acd77.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "4b0cf97b33826fd3737bcd3625007d4ef3ea8c81e36e35f40ef02ae7358bb51b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bbde9ca63cc1d862652f39618942e498f80634ffee106b0f87192bf48454dd75", "generation_seconds_batch": 16.408251077053137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.821704149246216, "target_z": 2.8906249920242844, "ce": 5.871703147888184, "genuineness": 4.250029563903809, "identity": 0.43260180950164795, "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/emo_Distress/4b0cf97b33826fd3737bcd3625007d4ef3ea8c81e36e35f40ef02ae7358bb51b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "4bba30574e7744349162b32ee58bee0fa65d5ff00d3a942f41ddaeed369145f2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cb36fb043a6e260a1021743c71364948c12a405b4cef691152d06b9d5fd379f3", "generation_seconds_batch": 22.559945516986772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24341824650764465, "target_z": -0.2636718714394127, "ce": 6.117925643920898, "genuineness": 4.7081804275512695, "identity": 0.480690598487854, "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/emo_Distress/4bba30574e7744349162b32ee58bee0fa65d5ff00d3a942f41ddaeed369145f2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "4bcb71a446cf7f2950c664b30fd99874120b6c73fff0148c9135a550a62a013b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9674e19752088c82674ad244d707a7b8395b6ae4ca629c15b56d239536b03d2b", "generation_seconds_batch": 17.221211244002916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.754037857055664, "target_z": 4.031249965818362, "ce": 5.518253803253174, "genuineness": 3.660081624984741, "identity": 0.6676461696624756, "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/emo_Distress/4bcb71a446cf7f2950c664b30fd99874120b6c73fff0148c9135a550a62a013b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "4bf8b1b3390357e8287f6c53649ab00f60ebb1f21afd2214168158e4f59088ab", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "28fce0d80ab89f2666fb05a34e59746c7c7d67cc7d055b397b91ce83c89a000a", "generation_seconds_batch": 23.2356517650187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22426070272922516, "target_z": -0.2871093731484946, "ce": 6.141753673553467, "genuineness": 4.8588056564331055, "identity": 0.6976905465126038, "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/emo_Distress/4bf8b1b3390357e8287f6c53649ab00f60ebb1f21afd2214168158e4f59088ab.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "4c7e75fc121824d61fd613f1e7b5cedd05e3a25fa77eb8168d035d7e3f91c3c9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b6de956056ef48f7a7c63db4e5199ab38e951825359972e5249ff2f43b8355e0", "generation_seconds_batch": 23.732408197945915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2418217808008194, "target_z": -0.2656250011393879, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.5991380214691162, "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/emo_Distress/4c7e75fc121824d61fd613f1e7b5cedd05e3a25fa77eb8168d035d7e3f91c3c9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "4c7ee2ec27def3602e63647a70ed6f5f51609e22a071a570c91434a4246636b4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1bc809a3a59b7065627ec0d0d8abfb2b0fb47bedeb430c6c5b0bdc94f863a6d4", "generation_seconds_batch": 23.66067499399651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.179311513900757, "target_z": 3.32812487808549, "ce": 5.629451274871826, "genuineness": 3.7040140628814697, "identity": 0.6749762892723083, "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/emo_Distress/4c7ee2ec27def3602e63647a70ed6f5f51609e22a071a570c91434a4246636b4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "4c8fdcf9724e682eeaef83d7f28d8fb1002dc5cc5bd17a2d94fe16232948bd7a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "eafb6569e7c722e9413b9d891e79fccfaa2e4277edd19cf132128641e370a043", "generation_seconds_batch": 20.341323441942222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3836586475372314, "target_z": 3.578124896315697, "ce": 5.974957466125488, "genuineness": 4.13078498840332, "identity": 0.3295004069805145, "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/emo_Distress/4c8fdcf9724e682eeaef83d7f28d8fb1002dc5cc5bd17a2d94fe16232948bd7a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "4ce7cc856138087a81e61b425471898c1b2443429c4dcc4b9fb149bc31cd0ef7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "77038bdaeaccb4c2f33245d2c2aceeadac8ea168fa4845d648656939460936d0", "generation_seconds_batch": 24.044036436942406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.918721616268158, "target_z": 0.5625000045575518, "ce": 5.585766792297363, "genuineness": 4.645420074462891, "identity": 0.7933639287948608, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis dis-moi quand tu es prêt.", "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/emo_Distress/4ce7cc856138087a81e61b425471898c1b2443429c4dcc4b9fb149bc31cd0ef7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "4dc7b9bc38362f22f94c0f2981a0a1a95181ed2cefd2cf3a825f9ce669d785b6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "cd22c0b675273abbf90722c8ae245c1d4da35b9c2e6368a9be34df54db621ee3", "generation_seconds_batch": 22.94620914303232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 5.645336627960205, "genuineness": 3.9550557136535645, "identity": 0.4017716944217682, "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/emo_Distress/4dc7b9bc38362f22f94c0f2981a0a1a95181ed2cefd2cf3a825f9ce669d785b6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "4e36a26963ef3c7cbf482bdeb081828c747578d369e72e9c918daa242de2476c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8254404321f72d2c58bec08973ba3bf355f401c679b5cc1693a27d453534e79c", "generation_seconds_batch": 21.491574328043498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.308258295059204, "target_z": 1.0390624846182628, "ce": 5.808161735534668, "genuineness": 4.432034492492676, "identity": 0.6185927391052246, "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/emo_Distress/4e36a26963ef3c7cbf482bdeb081828c747578d369e72e9c918daa242de2476c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "4e44eaf57d0c102603de821e3452ff024b62e3f2f2471cb07bcf1c09c39b7ae5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "18c5f9f8a55a343d55ffaf63a1f88de761b81c49848da0111e9edd0591cc8252", "generation_seconds_batch": 21.06169925199356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 5.673136234283447, "genuineness": 3.9299514293670654, "identity": 0.04188959300518036, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het touwraam. We kunnen er samen in kijken.", "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/emo_Distress/4e44eaf57d0c102603de821e3452ff024b62e3f2f2471cb07bcf1c09c39b7ae5.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": "4e82c831096724dcb8f43dc81626af40f0562fcaa22b8d6a44daa4f48c2ccfba", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "478e5128d18893504dd80e2dc31fe0cfad81339ba13d04a798228e2238d5dedd", "generation_seconds_batch": 15.905154419015162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1920831203460693, "target_z": 3.343749769843635, "ce": 5.895530700683594, "genuineness": 3.9425034523010254, "identity": 0.5480481386184692, "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/emo_Distress/4e82c831096724dcb8f43dc81626af40f0562fcaa22b8d6a44daa4f48c2ccfba.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "4e92020cc75c1c2ded469266a7233e3d891253200178e28d7358af8f61a2755e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "68a03f6af9523c003167fec6888fede1e52aa46860b2440b99f5211c985dda78", "generation_seconds_batch": 16.294037680956535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102970838546753, "target_z": 0.7968750581087852, "ce": 6.1020402908325195, "genuineness": 4.6956281661987305, "identity": 0.7356594800949097, "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/emo_Distress/4e92020cc75c1c2ded469266a7233e3d891253200178e28d7358af8f61a2755e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "4ea91a87dc8b7aeaef286c5d61c9fcda4b85918b0b8cfde1d0c730ea5bc240e9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d50457101d28a1dcc9ff1f9beb38f98517a90ec6f09f44cde21cb4a8595efe7b", "generation_seconds_batch": 19.028010499081574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28732094168663025, "target_z": -0.20996094141664606, "ce": 6.213237762451172, "genuineness": 4.6956281661987305, "identity": 0.6476483345031738, "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/emo_Distress/4ea91a87dc8b7aeaef286c5d61c9fcda4b85918b0b8cfde1d0c730ea5bc240e9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "4eea01732189cc42e0ce76badbcaca261470c0a4cad617c42ac01e9c4df22af6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9aaadc3facfdce8ba350f55e9867343b22c529cd0d0be146e136eb589345e140", "generation_seconds_batch": 22.07250287604984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8446695804595947, "target_z": 1.695312605393385, "ce": 5.478540420532227, "genuineness": 4.193545341491699, "identity": 0.5515586733818054, "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/manual-comparison-v1/audio/emo_Distress/4eea01732189cc42e0ce76badbcaca261470c0a4cad617c42ac01e9c4df22af6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "4ef641001e4f0011f6b6d5f689ca82fd30a886d75362840b17f30069ecfdc6b5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "aefc5933def79323f02b4e6fc8bf9d63f42755ffb1f9cec0e1c7aaeb68b2a155", "generation_seconds_batch": 21.92765883798711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6518642902374268, "target_z": 3.9062499567032583, "ce": 5.661221981048584, "genuineness": 3.722842216491699, "identity": 0.6199671030044556, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.3684210526315789, "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/emo_Distress/4ef641001e4f0011f6b6d5f689ca82fd30a886d75362840b17f30069ecfdc6b5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "4f48e70ebaf1faac1a7ba47cc2b47e2a369cb11514cf9a589fd42ca5a4d9c926", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "204362df43b7e9fbf0a471e9fd486ed7a6bbb7c5e54e6d9f09639fa6614e416a", "generation_seconds_batch": 21.836037456057966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9506508111953735, "target_z": 0.6015624527154003, "ce": 6.046441555023193, "genuineness": 3.8044304847717285, "identity": 0.6781603097915649, "hypothesis": "The door is s still open. I put your coat on the chair. Tell me when you are ready.", "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/emo_Distress/4f48e70ebaf1faac1a7ba47cc2b47e2a369cb11514cf9a589fd42ca5a4d9c926.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "4f4a27af8339e5bff0f4f5c2974616f5b349882f85393d91369b5849a3f04edf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "17df7b7110b879e97a6afc55bf4b8c37ca092c3fc2adc8113e5b9c73b79351d1", "generation_seconds_batch": 21.61119166004937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2003137767314911, "target_z": -0.3164062457272952, "ce": 6.1894097328186035, "genuineness": 4.7834930419921875, "identity": 0.5543490052223206, "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/emo_Distress/4f4a27af8339e5bff0f4f5c2974616f5b349882f85393d91369b5849a3f04edf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "4f4e1ded1331b6ed1892889c91a582c54130d71c5dd5e36f43d012a39fd9c962", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0e99e8fbcba0abd04be99e59e5bd04a780fadbe85dc81395f29615b02ad1763a", "generation_seconds_batch": 22.023857612046413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5700781345367432, "target_z": 1.3593750991267513, "ce": 6.022613525390625, "genuineness": 4.281409740447998, "identity": 0.6267824769020081, "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/emo_Distress/4f4e1ded1331b6ed1892889c91a582c54130d71c5dd5e36f43d012a39fd9c962.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "4f52d5d1d1635b23569c69b4b135a2b9c99720f2f3be6ab5994f1f6cdc7adbbd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "12cff0c87a0245083c783de8fa8808badd4efeaf08a8ec609730c5532321ed6b", "generation_seconds_batch": 21.207203656085767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5698946714401245, "target_z": 0.13574215865924263, "ce": 6.157639026641846, "genuineness": 4.331617832183838, "identity": 0.4906654953956604, "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/emo_Distress/4f52d5d1d1635b23569c69b4b135a2b9c99720f2f3be6ab5994f1f6cdc7adbbd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "4f760ce757355925e4f763353c6fa12a4b857f71978719af53094fe9e6db29a2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "73d7acfe7fbfcc5ae57c8b0c52dcdbfba0ae20931168d6dc6dfe6bb2614a37a6", "generation_seconds_batch": 16.18180844699964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.064366340637207, "target_z": 3.187499977212241, "ce": 5.506340026855469, "genuineness": 4.168440818786621, "identity": 0.5223773717880249, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/4f760ce757355925e4f763353c6fa12a4b857f71978719af53094fe9e6db29a2.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": "4f7cc6afe2117858e9ac13792b47622b9a2bac272cb802c213ac8eea7eec4edf", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0105f801a21c7f65905a2d287d6fbd958efc13d659a5a4a7df0501266047c53c", "generation_seconds_batch": 15.782312460942194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9877359867095947, "target_z": 3.093749751613428, "ce": 5.927301406860352, "genuineness": 3.936227321624756, "identity": 0.5662932395935059, "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": 0.03999999999999915, "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/emo_Distress/4f7cc6afe2117858e9ac13792b47622b9a2bac272cb802c213ac8eea7eec4edf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "4fc42ca9287868028a5566bc8e1e746ba1282cba2d7e25bc285d6281860cdc4a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "350f0341945976df967a779ec4fd32bcb67b19ea3938c0da47d9675119475e8e", "generation_seconds_batch": 23.60450974199921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.046441555023193, "genuineness": 4.457139015197754, "identity": 0.7878756523132324, "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/emo_Distress/4fc42ca9287868028a5566bc8e1e746ba1282cba2d7e25bc285d6281860cdc4a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "4fe437b855dac09d395a10ae8c8db15f493a00ae391527751ca720678d6fe385", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a54dcbc958797d76420a18d9131cdb31d21b7c022d52de660b397a457c07299b", "generation_seconds_batch": 20.767590621951967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1428411602973938, "target_z": -0.3867187326243338, "ce": 5.982900142669678, "genuineness": 4.582659721374512, "identity": 0.6814547777175903, "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/emo_Distress/4fe437b855dac09d395a10ae8c8db15f493a00ae391527751ca720678d6fe385.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "5104bec0d2a47c4430141ee105ff8c949c0d22400ba4c3dcc24b48d42a226ac7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a3d46891be18a5afebedc9a0c739482e52fe757cf694649170166fca8f5dce09", "generation_seconds_batch": 22.799022796098143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.562462329864502, "target_z": 3.7968748393463, "ce": 5.1469340324401855, "genuineness": 3.6663577556610107, "identity": 0.6509603261947632, "hypothesis": "J'ai... j'ai trouvé ta petite boîte. Elle était... elle était près de la vieille fenêtre. Nous. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.2631578947368421, "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/emo_Distress/5104bec0d2a47c4430141ee105ff8c949c0d22400ba4c3dcc24b48d42a226ac7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "51151645bf2164319549b0354eb472d50a881d908d8b6115a5cf70a3e25b57e6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dd73a30ca32a6ecb332b414d273f06620f086a4c763dce69923481c96e49c776", "generation_seconds_batch": 21.381141050020233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.642900228500366, "target_z": 2.6718747573103676, "ce": 5.190618991851807, "genuineness": 3.8044304847717285, "identity": 0.5511739253997803, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que adentro.", "wer": 0.11764705882352941, "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/emo_Distress/51151645bf2164319549b0354eb472d50a881d908d8b6115a5cf70a3e25b57e6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "511bdcf79b98fc415de0cf785f9211b4ca073db1ed318c190600350411817ecc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d10cbc6d28aaae99c566b13eb8c9888c022b5e45c256e2adca3e719731d0458f", "generation_seconds_batch": 16.243462050915696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26257580518722534, "target_z": -0.24023435150012365, "ce": 6.213237762451172, "genuineness": 4.7834930419921875, "identity": 0.5558614134788513, "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/emo_Distress/511bdcf79b98fc415de0cf785f9211b4ca073db1ed318c190600350411817ecc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "51542d984788b062ba748991c217d02623e23f91d5781288046e440b2d854fa8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a6b5f8e136660a41c1d56fc256ae60a54daee6deda6d66d292f8555646dfef09", "generation_seconds_batch": 20.94426808494609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4876769185066223, "target_z": 0.03515626167872644, "ce": 5.418970584869385, "genuineness": 4.118232727050781, "identity": 0.4443594217300415, "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/emo_Distress/51542d984788b062ba748991c217d02623e23f91d5781288046e440b2d854fa8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "51f9e1ae6dfa592e7a191ebe22aeb709f7d3fb2085292a13b19280292cf44c85", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6a6caece026d0036cac4c130473404599736851ec073e3e6f897ebbbd30a133f", "generation_seconds_batch": 20.96919816196896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9072980880737305, "target_z": 4.21874983364936, "ce": 5.178704738616943, "genuineness": 3.587907314300537, "identity": 0.18633857369422913, "hypothesis": "Ik heb het kleine doosje gevonden. Dat stond. Naast het oude raam kunnen we samen in kijken.", "wer": 0.16666666666666666, "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/emo_Distress/51f9e1ae6dfa592e7a191ebe22aeb709f7d3fb2085292a13b19280292cf44c85.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "52b65b5c92fb88d6094be8f3febf4d7c5d58f004b97bad67aff311d060801325", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4568233bdac26c18de20ea1cbb07a61523e60ab5ee1ad6670c99cc5d6bab61aa", "generation_seconds_batch": 20.945069725974463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1677696704864502, "target_z": 0.8671875085454096, "ce": 6.006728172302246, "genuineness": 4.168440818786621, "identity": 0.45468848943710327, "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/emo_Distress/52b65b5c92fb88d6094be8f3febf4d7c5d58f004b97bad67aff311d060801325.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "530d6c643ff0b33563e9c2757b015b950d6479ff0dd6a9a1617e2393e2e1c94a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4246462029850f9854834dd81b8778251743fe3d2f3ecbf1c6b792c4fa3d37f9", "generation_seconds_batch": 20.94426808494609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.732302188873291, "target_z": 2.781249874667326, "ce": 5.927301406860352, "genuineness": 4.362998008728027, "identity": 0.6233829855918884, "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/emo_Distress/530d6c643ff0b33563e9c2757b015b950d6479ff0dd6a9a1617e2393e2e1c94a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "5311dd3f88133c43f25a6364581dce87dfab098311c3001207dcb9847ec0d6f6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6180e59ff458d57f7f21252f92d4ea245a0316b497c09f675864c66ced932430", "generation_seconds_batch": 20.146268317941576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.681215524673462, "target_z": 2.7187500159514313, "ce": 5.274016857147217, "genuineness": 3.653805732727051, "identity": 0.4642351567745209, "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/emo_Distress/5311dd3f88133c43f25a6364581dce87dfab098311c3001207dcb9847ec0d6f6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "53765c149c14672e3bbeec43741912f9a69caaea8ae4234c03c7ddcf5b9667c3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e3b59c394c439d19f176d4c76b953eb6c2967ae86783b08b950f48e908bd4407", "generation_seconds_batch": 23.104672770947218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 5.502368927001953, "genuineness": 3.9801597595214844, "identity": 0.6341037154197693, "hypothesis": "La portée la tête encore ouverte 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/emo_Distress/53765c149c14672e3bbeec43741912f9a69caaea8ae4234c03c7ddcf5b9667c3.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": "5399abea107449c43e6b6d8258e5ae26b482512f3739f2adf8637d97e4d5a419", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3db5774c8d9d46ac188ec2415520cb72ffec381c8166e49982cf2bf25754e671", "generation_seconds_batch": 15.798881446942687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3581151962280273, "target_z": 3.5468748211160928, "ce": 5.804190158843994, "genuineness": 3.8671910762786865, "identity": 0.6807814240455627, "hypothesis": "Las llaves están en la mesa de la cocina. Mire, en el cajón. Y luego junto a la ventana. Llévatelas cuando te vayas.", "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/emo_Distress/5399abea107449c43e6b6d8258e5ae26b482512f3739f2adf8637d97e4d5a419.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "53d1e057907282bd7e1569a0bb96782197f7e4b4f96a51b38436ffd5b0e84224", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d2b48bcb52eb2f23d9e53077788c852e6a28e13c08768fcdebbb3e233ef481ef", "generation_seconds_batch": 22.107084238901734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.949420928955078, "target_z": 3.0468747846556785, "ce": 5.855817794799805, "genuineness": 3.9550557136535645, "identity": 0.6014615297317505, "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/emo_Distress/53d1e057907282bd7e1569a0bb96782197f7e4b4f96a51b38436ffd5b0e84224.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "54591fca9f9aca6af6dc844faf5e7fdf74c4096778d1216713f642d80a0dc448", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "2f415e9590aa2b6cc38938d0fa2961887a6b04a4556fcc91330b36d3e1150fcb", "generation_seconds_batch": 24.417777566006407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28492623567581177, "target_z": -0.21289064508171252, "ce": 5.895530700683594, "genuineness": 4.482243061065674, "identity": 0.5894914865493774, "hypothesis": "Te encontrado la cajita. Estaba junto a la ventana. Vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/54591fca9f9aca6af6dc844faf5e7fdf74c4096778d1216713f642d80a0dc448.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "5459c76882b657425e94dd0c42be1027abec3489e7955f891e2c2c5aac39e2b1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "146c976a57b7336abc1ccd2e98e8cd93fbfbb50825a2d675ffaa943c9777a90e", "generation_seconds_batch": 14.131936536054127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7195305824279785, "target_z": 2.765624982909181, "ce": 5.871703147888184, "genuineness": 4.250029563903809, "identity": 0.6710741519927979, "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/emo_Distress/5459c76882b657425e94dd0c42be1027abec3489e7955f891e2c2c5aac39e2b1.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "a723ea50e070afea1d1ca116cb3db35ec49dc0faaeb037167d2de6ff2b03add1", "generation_seconds_batch": 17.89608310488984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13645529747009277, "target_z": -0.39453125142423495, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.35020339488983154, "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/emo_Distress/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "54c99e351d59d42abbfb2b95d37f19e17bbf2e53e441d99b9067f32976aa0800", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "82d8a261df313ed103885d02cad993da3129585f604660cdb22d33effd425011", "generation_seconds_batch": 22.957366917049512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.566270112991333, "target_z": 2.5781248233948686, "ce": 5.871703147888184, "genuineness": 3.7918784618377686, "identity": 0.5823044776916504, "hypothesis": "He encontrado la cajita. Estaba junto a. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.17647058823529413, "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/emo_Distress/54c99e351d59d42abbfb2b95d37f19e17bbf2e53e441d99b9067f32976aa0800.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "54f6b4d4c3a56ad3f9336a759f7ca9312bc90cddbfcd4dee50f0b179f5847428", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d15fee1b0e2131965cb87ff72363e336c7c115b7f9215bdac60473be680cf166", "generation_seconds_batch": 22.87724204303231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7941975593566895, "target_z": 0.4101562161032086, "ce": 5.959072113037109, "genuineness": 4.005263805389404, "identity": 0.4146346151828766, "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/emo_Distress/54f6b4d4c3a56ad3f9336a759f7ca9312bc90cddbfcd4dee50f0b179f5847428.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "5506d1c82b41cc981982152c2c8b9ec04ca685aed6c2699499047954db21196b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3736866b0ad2409eb90f55053587a6861ad9ee258c8832aadad3b3659e849dd6", "generation_seconds_batch": 21.69943397201132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209277629852295, "target_z": 0.9179686984426955, "ce": 5.982900142669678, "genuineness": 4.570107460021973, "identity": 0.6358109712600708, "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/emo_Distress/5506d1c82b41cc981982152c2c8b9ec04ca685aed6c2699499047954db21196b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "5509081e9d11c05062e9e7b436cb728fe2ac6bc317b4871f06fae7d06cdd2039", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "96708bfb29ad3cedd7427270e16b2a246c3c5916fa75182c12af3260cce449cf", "generation_seconds_batch": 22.569465843960643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8817546367645264, "target_z": 4.187499758449755, "ce": 5.708878040313721, "genuineness": 3.7291181087493896, "identity": 0.5721728801727295, "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/emo_Distress/5509081e9d11c05062e9e7b436cb728fe2ac6bc317b4871f06fae7d06cdd2039.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "56488f08c2a286ed3570ce1dcc798c0d07651b1198c990ed33b53b36efaf3c84", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4418a8b1e5137b835682a5298d5373f1d0ddacc03ca5ff1210c5904909bdc8f2", "generation_seconds_batch": 24.044036436942406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3363797664642334, "target_z": 2.296875021648371, "ce": 6.078212261199951, "genuineness": 4.243753433227539, "identity": 0.7480366230010986, "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/emo_Distress/56488f08c2a286ed3570ce1dcc798c0d07651b1198c990ed33b53b36efaf3c84.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "5703b602c5797b67f70e81b3838111e6b5013db48afbe5417b757ddd587b5fed", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8ddedcddea397cbe2a73439380c7070a3e95f2aa024ac8dc3111488e17be11ff", "generation_seconds_batch": 21.877632772899233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.511375665664673, "target_z": 3.7343749806304047, "ce": 5.855817794799805, "genuineness": 3.6914620399475098, "identity": 0.5261443853378296, "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/emo_Distress/5703b602c5797b67f70e81b3838111e6b5013db48afbe5417b757ddd587b5fed.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "57731f09d2335ef4bdc713eaa65822722d28373a8c7fcc4ab3fa8f8356642e2d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "16fedb144512648f751258406a986131a950d214aa92af29f26f1b37b7466b6a", "generation_seconds_batch": 21.91172292898409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1843491494655609, "target_z": -0.3359375062666337, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.4327910542488098, "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/emo_Distress/57731f09d2335ef4bdc713eaa65822722d28373a8c7fcc4ab3fa8f8356642e2d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "577f6ae1264e8298985987b8bfe2eef0ee4551f87a71d2461b83bec03c8a0563", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d3eb32c96de074590091df2e1c0af6aeeca7c754aeffeab9b3839bc3bd4ce153", "generation_seconds_batch": 22.031475202995352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19871732592582703, "target_z": -0.3183593571970634, "ce": 6.23706579208374, "genuineness": 4.557555198669434, "identity": 0.643609881401062, "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/emo_Distress/577f6ae1264e8298985987b8bfe2eef0ee4551f87a71d2461b83bec03c8a0563.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": "5798fe60f594176d271f68dd0c63938b4210e1c8649014a781d98b106cf81eac", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb1b015e404d182605fd4d487ac5abd300a03e4ff5271edee9a5698e19b4debc", "generation_seconds_batch": 21.67797936697025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2176265716552734, "target_z": 3.3749998450432397, "ce": 5.982900142669678, "genuineness": 3.6851859092712402, "identity": 0.0653025358915329, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "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/emo_Distress/5798fe60f594176d271f68dd0c63938b4210e1c8649014a781d98b106cf81eac.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": "58590fae20bfce19583166d74ef947918f6650aacccc2023b70f1310fb6abbf4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0dc422c71342a423c0eabf49f2e028d4fe8d659c55c0fdc10ee9ea51e50e40e9", "generation_seconds_batch": 16.671182858990505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3325717449188232, "target_z": 3.5156247459164884, "ce": 5.414999485015869, "genuineness": 3.7918784618377686, "identity": 0.5954291820526123, "hypothesis": "Da eine Nachricht kam, sie schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "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/emo_Distress/58590fae20bfce19583166d74ef947918f6650aacccc2023b70f1310fb6abbf4.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": "5878e1c187000c8e0844066ddf595d4e85869333f9775a946de3f33822b29f62", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2505047e72be765bea0e4a83ac1733c380606ea1d17b469813c69e21650a7a32", "generation_seconds_batch": 17.035639966954477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.25594162940979, "target_z": 3.421874812000989, "ce": 5.863759994506836, "genuineness": 4.017816066741943, "identity": 0.030115431174635887, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de la en daarna naar Snachterlaam. Neem ze mee als je weggaat.", "wer": 0.18181818181818182, "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/emo_Distress/5878e1c187000c8e0844066ddf595d4e85869333f9775a946de3f33822b29f62.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "589aff0920f97595d88ab76aeb9f8a0efbee2dd19e36078c50740cac23ce3e4a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ebe2fa68c726836e0e6f7cb8cd231cc779043462cf792ee8be930bcfe753a06e", "generation_seconds_batch": 14.275523404008709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4541512131690979, "target_z": -0.0058593708697187, "ce": 6.1020402908325195, "genuineness": 4.369274139404297, "identity": 0.2856062054634094, "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/emo_Distress/589aff0920f97595d88ab76aeb9f8a0efbee2dd19e36078c50740cac23ce3e4a.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": "58cbef9870f557c7500e6091973662e7bdc095ab231b626eee7ee18326c42b0b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19c64238109b01fe128d07f4dd219c4e7ca27616014f14847e77d4c755b54834", "generation_seconds_batch": 20.859526848071255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7706172466278076, "target_z": 2.8281248416250757, "ce": 5.911416053771973, "genuineness": 3.7793264389038086, "identity": 0.7115687131881714, "hypothesis": "Schrieb die Nummer auf den Umschlag. Lies 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/emo_Distress/58cbef9870f557c7500e6091973662e7bdc095ab231b626eee7ee18326c42b0b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "58d424c00cb2e7dde8b220a0a513e3b2159fcdd8cceb9bac8a1c6423bbbc1dd0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e42c7d95fa7dc7d5cd2fc773e0e9dd8572c50118b0debbfe85e41528967e61f3", "generation_seconds_batch": 15.736601160955615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05663219094276428, "target_z": -0.49218751766051316, "ce": 6.443574905395508, "genuineness": 4.457139015197754, "identity": 0.580997884273529, "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/emo_Distress/58d424c00cb2e7dde8b220a0a513e3b2159fcdd8cceb9bac8a1c6423bbbc1dd0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "58d69be1022404e998dfc171009918e95f194f031dd1cf23d45d21bac2066288", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "11b886b1f4385b1e5de74df8ea3179fb769cea8b2830f391e56ff76889b5494c", "generation_seconds_batch": 21.41895077296067, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0515944957733154, "target_z": 3.171874793770782, "ce": 5.744620323181152, "genuineness": 4.268857479095459, "identity": 0.7379562854766846, "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/emo_Distress/58d69be1022404e998dfc171009918e95f194f031dd1cf23d45d21bac2066288.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "58e8623a522308321fc71b0e39e4bab100f7389f84b75bbedce45071cabd7170", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "bc69c4d57a0e730c55b662a862ce87500d0187a1599abd2309ed30688710c5bf", "generation_seconds_batch": 14.845030892058276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6457266211509705, "target_z": 0.22851560976068624, "ce": 6.022613525390625, "genuineness": 4.507347106933594, "identity": 0.7154186964035034, "hypothesis": "La porte est encore ouverte. Hein ? J'ai posé du cils en enceint sur l'allée en chaise. Dis-moi quand tu es prêt.", "wer": 0.3888888888888889, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/58e8623a522308321fc71b0e39e4bab100f7389f84b75bbedce45071cabd7170.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "59a3abfbf289147b95fda0b2cc59e9a7c55d5cbbec83ab1ef3b62c2d88a91e05", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c8af219abaa087c2c8d59a3889d774c5bff42194f2ed38ac61e73c47ba818a8e", "generation_seconds_batch": 21.528664737939835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8344757556915283, "target_z": 2.9062498837824298, "ce": 6.09409761428833, "genuineness": 3.7416701316833496, "identity": 0.627899706363678, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "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/emo_Distress/59a3abfbf289147b95fda0b2cc59e9a7c55d5cbbec83ab1ef3b62c2d88a91e05.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "5a001981f0a515fec0425b362acfcf4f2d066c17fc83c46192aa2002f75f5ad4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f02b15b9f80747369f5ac552d856ecbb3b1fadc213b825ab8396039d83d8eda", "generation_seconds_batch": 23.446964450064115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1316659152507782, "target_z": -0.4003906222939536, "ce": 6.006728172302246, "genuineness": 4.532451152801514, "identity": 0.645805835723877, "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/emo_Distress/5a001981f0a515fec0425b362acfcf4f2d066c17fc83c46192aa2002f75f5ad4.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": "5a2dab4424284553ff9c9a231cac9da855e6b22196c6a05e07d45110c42bd8af", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73c631467b2b32f04f1528e32171ac3bcbe4fc5867b23206da760dd7010b64ea", "generation_seconds_batch": 16.379096765071154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8101621866226196, "target_z": 0.42968747664254714, "ce": 6.23706579208374, "genuineness": 4.055472373962402, "identity": 0.5390318632125854, "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/emo_Distress/5a2dab4424284553ff9c9a231cac9da855e6b22196c6a05e07d45110c42bd8af.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": "5a36fbba3a846c71bc37db9a404c00a09341a8d96053b7c84bff97371910486d", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cc20dc8263461d59f66881010402db240707f2a8ca34d75bbe23aba5c267f71", "generation_seconds_batch": 22.34894807008095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8817546367645264, "target_z": 4.187499758449755, "ce": 5.6413655281066895, "genuineness": 3.600459337234497, "identity": 0.6360104084014893, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Cando en ido. Llámame, llámame cuando tenga su momento.", "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/emo_Distress/5a36fbba3a846c71bc37db9a404c00a09341a8d96053b7c84bff97371910486d.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": "5a9a8b490625f2c5e5195c3fe29adeabdde9da4023a7576f6a5248c3fb3fdf34", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d52becc49c06650335d2a4e264f335519dc02f2e0c861a70a48aa62e1d166080", "generation_seconds_batch": 18.449761335970834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.655672073364258, "target_z": 2.687499940751827, "ce": 5.879645347595215, "genuineness": 4.036643981933594, "identity": 0.5534621477127075, "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/emo_Distress/5a9a8b490625f2c5e5195c3fe29adeabdde9da4023a7576f6a5248c3fb3fdf34.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "5b2004ad276eabf683c92c1ddd726ef12fe1acce037c724d43f32e1ba0d011df", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "daee8a4a38ff9e1e784836e0727b1e2d1791ed4c507e1e6b7651e489b370a10a", "generation_seconds_batch": 21.48097402602434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5790419578552246, "target_z": 2.5937500068363275, "ce": 5.831989288330078, "genuineness": 4.105680465698242, "identity": 0.1130634993314743, "hypothesis": "De deur staat nog open. Ik heb je het 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/emo_Distress/5b2004ad276eabf683c92c1ddd726ef12fe1acce037c724d43f32e1ba0d011df.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "5b6cde57ab68cfc09e443463e7690d4c39cacfa8c6132f8fa299ae4a367e64e1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "fe10b9bb5ae61cfa856ce9e0a01528bf02c775cffd351c4b254b25029f74fb60", "generation_seconds_batch": 22.003738892031834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20829609036445618, "target_z": -0.30664061545762594, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.5673884153366089, "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/emo_Distress/5b6cde57ab68cfc09e443463e7690d4c39cacfa8c6132f8fa299ae4a367e64e1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "5b8bbe0d0d3c33edb9dd1ce5cce7d7933b8bcbc447b317e57f9dae5d58426209", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "76e3b1262c35b6cab9f720c7d0fc503defa3b5623ea9f4d033fd11109f9953fd", "generation_seconds_batch": 20.20240039692726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0847536325454712, "target_z": 0.7656249829091808, "ce": 5.990842819213867, "genuineness": 4.3504462242126465, "identity": 0.576363205909729, "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/emo_Distress/5b8bbe0d0d3c33edb9dd1ce5cce7d7933b8bcbc447b317e57f9dae5d58426209.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "5bddb9a6b9055d046162a37fdd7d64d3928d66d8dd658fc9e28449c1c96208e0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7bcacce5ae6bf3b2bd79779d2f580798c17876648d4c91bb99e13a4e6385b3ca", "generation_seconds_batch": 22.161793753039092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9442650079727173, "target_z": 0.5937500068363276, "ce": 6.1894097328186035, "genuineness": 4.337893962860107, "identity": 0.6712552309036255, "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/emo_Distress/5bddb9a6b9055d046162a37fdd7d64d3928d66d8dd658fc9e28449c1c96208e0.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": "5becc907b7d3575ca9648289a320c69e205ff346495d468705f2fffbeeee1ce7", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5360b4ed34e11903ec0f0b44658f3c6c5a68034c572af926932129b62157205", "generation_seconds_batch": 15.661036713048816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 5.7684478759765625, "genuineness": 4.042920112609863, "identity": 0.7137565016746521, "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/emo_Distress/5becc907b7d3575ca9648289a320c69e205ff346495d468705f2fffbeeee1ce7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "5bf0f19f8a25e29e8895db25b26dfe03c3018ebccbc2ca334ff19b4c9007c3f7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f289ede2896f3fb9f1a582833149cede9c1a6d2639425414ce2304c6b06fa3a2", "generation_seconds_batch": 20.862136048963293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2753474712371826, "target_z": -0.22460938682114992, "ce": 6.181467056274414, "genuineness": 4.3504462242126465, "identity": 0.40511035919189453, "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/emo_Distress/5bf0f19f8a25e29e8895db25b26dfe03c3018ebccbc2ca334ff19b4c9007c3f7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "5c09c71f7fffb7abf999aa26ff7b5f3333305b45f8a832c83db851eda8fd9e65", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0ff5074ad15b564a5480a6e3c1b7bbb2cffefacd7eb87d0b20e6093d1c2c8f59", "generation_seconds_batch": 16.200483538093977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7207603454589844, "target_z": 0.32031250512724574, "ce": 6.252951145172119, "genuineness": 4.65797233581543, "identity": 0.7190766334533691, "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/emo_Distress/5c09c71f7fffb7abf999aa26ff7b5f3333305b45f8a832c83db851eda8fd9e65.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "5c59e140fa7c316ca4a76dc80f9a835b4d1ee82f6c65f9d344738eb079167d38", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a727ecf56e4658d47e28f171c2b4e5c578f198f671358ad3e20077bb88ee0b77", "generation_seconds_batch": 20.20240039692726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2968997359275818, "target_z": -0.19824216321679441, "ce": 5.863759994506836, "genuineness": 4.457139015197754, "identity": 0.5644209384918213, "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/emo_Distress/5c59e140fa7c316ca4a76dc80f9a835b4d1ee82f6c65f9d344738eb079167d38.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "5c8c1b13ff58b09fb1fb24eb05253952cc6020acc924cfccfe8921e23b50040b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "ca636a2887fb7ba823531c63a3f155636cb813eb68405cf05baf1c7ac22638c2", "generation_seconds_batch": 22.183130132965744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.418970584869385, "genuineness": 3.722842216491699, "identity": 0.535365104675293, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es préparé mon piste. Tcham. Dis pourquoi est-ce qu'on se dit pas.", "wer": 1.0555555555555556, "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/emo_Distress/5c8c1b13ff58b09fb1fb24eb05253952cc6020acc924cfccfe8921e23b50040b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "5d14da95cc211adbd403c490beef67e14597d594a61b756ee81f676b368976b5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8240739ca125c52c0a7325b58f4afae8f5af00ff8c5e0e146d5b3d5daa9e4d48", "generation_seconds_batch": 21.143690889002755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 5.935244083404541, "genuineness": 3.9048471450805664, "identity": 0.3552747368812561, "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/emo_Distress/5d14da95cc211adbd403c490beef67e14597d594a61b756ee81f676b368976b5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "5d923f66c2880c19115576b1efa0cb11e69cdee30fa1b5acce8030d7e2e84575", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ff392ca2a8c9fbe49bc21befa3e2cafe0f687cbbbd58ac54d51fe706d42f8308", "generation_seconds_batch": 22.183130132965744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2176265716552734, "target_z": 3.3749998450432397, "ce": 5.6254801750183105, "genuineness": 4.049196243286133, "identity": 0.6935558915138245, "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/emo_Distress/5d923f66c2880c19115576b1efa0cb11e69cdee30fa1b5acce8030d7e2e84575.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "5dc560f0dad6454d0d0993b413648d12af4732482123b58d2f02fde2d5e715ae", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0803252885ca76f7a4fa16c67f04bb35925af33a49286fce8cea0f882da6d783", "generation_seconds_batch": 21.601180746918544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06301805377006531, "target_z": -0.4843749988606121, "ce": 6.3641486167907715, "genuineness": 4.507347106933594, "identity": 0.6299723386764526, "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/emo_Distress/5dc560f0dad6454d0d0993b413648d12af4732482123b58d2f02fde2d5e715ae.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "5de0f79e07bc24a8830817868f2b82695dc53d153035688ae69b7f13e9237670", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7a099d86843e8e20579a59b342b0e307ae679e6af3431de2e52414a02b05dc49", "generation_seconds_batch": 21.816190349985845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06940388679504395, "target_z": -0.4765625165211252, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.5314221382141113, "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/emo_Distress/5de0f79e07bc24a8830817868f2b82695dc53d153035688ae69b7f13e9237670.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": "5de5d95097702094b9fa7f8321d78da5d42011e69def3542d652795745d4f1ed", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9daceee6876fe6517fc92e153daebeb529a01aa9f7ac1bccc611c4c3ee85c969", "generation_seconds_batch": 16.113896563998424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8600192070007324, "target_z": 2.937499958982034, "ce": 5.609594821929932, "genuineness": 3.71028995513916, "identity": 0.6974759101867676, "hypothesis": "Quelqu'un a déplacé la petite geste bleue ! Elle était ici, près de la grande bibliothèque. Nous la remettrons auprès de déjeuner.", "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/emo_Distress/5de5d95097702094b9fa7f8321d78da5d42011e69def3542d652795745d4f1ed.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "066123fad77570d136dad9e658bd9e0e740602246f49c6ffc5d915503d4e65d6", "generation_seconds_batch": 14.757277628988959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1891385316848755, "target_z": -0.330078135396915, "ce": 6.078212261199951, "genuineness": 4.2374773025512695, "identity": 0.7691301107406616, "hypothesis": "La route tourna gauche après le pont. Continue jusqu'à la petite barrière en bois. Je je t'attendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "5e3840df7a65461d19d3d9e76d7ed2b801640dc16c835b14ade7747a541dd2d9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ff9e11cd4676a720381ac66f2a4881cbb5dd1e32c9317e0fc02352bc7e388d6a", "generation_seconds_batch": 20.45624362595845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.157576084136963, "target_z": 2.0781250786177683, "ce": 5.752562999725342, "genuineness": 4.287685871124268, "identity": 0.6789315342903137, "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/emo_Distress/5e3840df7a65461d19d3d9e76d7ed2b801640dc16c835b14ade7747a541dd2d9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "5e3bb0a66279a9d7c00788f18b945d5bd866ce620fc0556c36b2e4d5d604ec30", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "82dc1e4d5cc9edd2f7ba4bd71039e8b59f35e9f308d5d3dd89a6530ad68b9d29", "generation_seconds_batch": 17.56610898906365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.115453004837036, "target_z": 3.249999835928136, "ce": 5.967014789581299, "genuineness": 4.011539936065674, "identity": 0.5789036154747009, "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/emo_Distress/5e3bb0a66279a9d7c00788f18b945d5bd866ce620fc0556c36b2e4d5d604ec30.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "5e80986db22f77f6cbdf5d183644a0ce6ed60e0c3599a535fa67ace0afbd5a98", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bd5d8152b5da6f4eb3f5e25b12484da10e0c43831710062c8f38c86199baa7a4", "generation_seconds_batch": 21.95400247001089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602007269859314, "target_z": 1.3984374743637713, "ce": 5.935244083404541, "genuineness": 4.545003414154053, "identity": 0.622699499130249, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "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/emo_Distress/5e80986db22f77f6cbdf5d183644a0ce6ed60e0c3599a535fa67ace0afbd5a98.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "5e85551f4d234db14d07c12d3b00c9732a8f4ffec681b748cd939ceaec15c327", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "00412540fcf796ac18bd910ad6bd22c09a3878d687acf3da1e5d1cd7d46f40c1", "generation_seconds_batch": 15.889340206049383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5534985065460205, "target_z": 2.562499931636723, "ce": 5.863759994506836, "genuineness": 4.036643981933594, "identity": 0.8109173774719238, "hypothesis": "La porte. La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Je suis parti. Quand on entend qu'il y ait. Tout qu'il a fait ma chaise.", "wer": 0.9444444444444444, "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/emo_Distress/5e85551f4d234db14d07c12d3b00c9732a8f4ffec681b748cd939ceaec15c327.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "5ea6080a66ae5a8fb62829c4cb941a3554662cbe2e5b91eace68368a394a8c77", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a52defe1730f454d10571a0f18b5e94a0f9a1e837e25ce25b3be447c50a60e07", "generation_seconds_batch": 22.78501379303634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.281485080718994, "target_z": 3.4531248872005933, "ce": 5.661221981048584, "genuineness": 3.923675537109375, "identity": 0.757114052772522, "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/manual-comparison-v1/audio/emo_Distress/5ea6080a66ae5a8fb62829c4cb941a3554662cbe2e5b91eace68368a394a8c77.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "5f0ee7fed5b437453f70dca82cf87fbc708478ce9a7006733584aabc5a02e168", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "74a2afd89167455d64211666c84b20bc1f1ee69ec23ceb2929eb19b8ef53aaf7", "generation_seconds_batch": 21.323935832013376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4541512131690979, "target_z": -0.0058593708697187, "ce": 6.086154937744141, "genuineness": 4.362998008728027, "identity": 0.5765981674194336, "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/emo_Distress/5f0ee7fed5b437453f70dca82cf87fbc708478ce9a7006733584aabc5a02e168.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "60d0d38e59d1a30e41e37a57d7b59711872d054bac0b8fbdbf4cc896960af5b4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a69998cb317008f1a3913bdd99f40fcbf0f2d8f2da4ee897867ca9f9e1815087", "generation_seconds_batch": 21.381141050020233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8344757556915283, "target_z": 2.9062498837824298, "ce": 5.621508598327637, "genuineness": 3.7793264389038086, "identity": 0.6090461015701294, "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/emo_Distress/60d0d38e59d1a30e41e37a57d7b59711872d054bac0b8fbdbf4cc896960af5b4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "6189da80e9eb516011728defafd38c15604709f565f4369acde07ce985faab9f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f8670531d270473f2cf64ad79455453e57d2f286d7a617db17d5f9b8aa72a3a1", "generation_seconds_batch": 22.006442469079047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09973669052124023, "target_z": -0.4394531069122164, "ce": 6.268836498260498, "genuineness": 4.482243061065674, "identity": 0.6198581457138062, "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/emo_Distress/6189da80e9eb516011728defafd38c15604709f565f4369acde07ce985faab9f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "61e67de5ba1779d0f94513d2376491b88e1fe38fcd3139928b4258f993fca0ef", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4ffd15c29fb33229359844ca45b12eb29c5b710226bb7e63ec9fb48b387d31a0", "generation_seconds_batch": 22.608008089940995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38390690088272095, "target_z": -0.09179685890614528, "ce": 6.213237762451172, "genuineness": 4.319066047668457, "identity": 0.7369269132614136, "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/emo_Distress/61e67de5ba1779d0f94513d2376491b88e1fe38fcd3139928b4258f993fca0ef.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "622a6a45896be41ae4ca259eba55f0d0b6ddf48d8bfc7e8631f9ff19f4911861", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "67952b06c3034bcfd41b59cbfcf74d023261aba912593501a1287b2af42ce8f4", "generation_seconds_batch": 23.118824679986574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22905008494853973, "target_z": -0.2812500022787759, "ce": 6.038498878479004, "genuineness": 4.011539936065674, "identity": 0.6426093578338623, "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/emo_Distress/622a6a45896be41ae4ca259eba55f0d0b6ddf48d8bfc7e8631f9ff19f4911861.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": "633f6f6c79f5091a777642f80e2eef94184c7aba05eb636b041556c81caa37ee", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "83fb2cae3fca41a340a4af04c7d680508cccd2188f373995f7b23b18001dc4b0", "generation_seconds_batch": 16.55699996300973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9366493225097656, "target_z": 3.031249892897533, "ce": 5.9431867599487305, "genuineness": 3.7165660858154297, "identity": 0.4162209630012512, "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/emo_Distress/633f6f6c79f5091a777642f80e2eef94184c7aba05eb636b041556c81caa37ee.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "64246e5ff2a49dc0a4ad5acad6578eff2152403d331cdf7695e370a18177a34e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a913681ba973610704bbe641720248ea37a730524fad7541746475f4d6696647", "generation_seconds_batch": 21.02232220210135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8344757556915283, "target_z": 2.9062498837824298, "ce": 5.95112943649292, "genuineness": 4.055472373962402, "identity": 0.46875834465026855, "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/emo_Distress/64246e5ff2a49dc0a4ad5acad6578eff2152403d331cdf7695e370a18177a34e.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": "64a6ebddae5bf016d343066e5df3e608b7f00d9a56d46c2e4e7a9686585cd444", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f400922b2072311d76a97fb8e13b9c6143d1bc16897eee662a813b23e77dc2d1", "generation_seconds_batch": 16.499845883110538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2060847282409668, "target_z": 0.9140624755031592, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.6114723086357117, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed. Ik controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "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/emo_Distress/64a6ebddae5bf016d343066e5df3e608b7f00d9a56d46c2e4e7a9686585cd444.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "652a3da0ed418b9c6dd820ad8ff99b064c91413682bbb666aacbbf116726d08c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6c6ae13a3961c3fd2078d97c68a001d2d9edf892b68d77bd80dcc0052ecdec6f", "generation_seconds_batch": 18.408764499938115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.710566759109497, "target_z": 1.5312500751996043, "ce": 6.0146708488464355, "genuineness": 4.406930446624756, "identity": 0.5541988015174866, "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/emo_Distress/652a3da0ed418b9c6dd820ad8ff99b064c91413682bbb666aacbbf116726d08c.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": "6566a9ea7d1cfdaf19e791fdd7a99c291a02298f9e9434a6f75d089550028b77", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1335cc0ab65229a4854b2e413749788a208e40a2fd426dd305e6b12775982d3f", "generation_seconds_batch": 16.532636835006997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 5.696964263916016, "genuineness": 3.4215922355651855, "identity": 0.6480849385261536, "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": 0.03999999999999915, "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/emo_Distress/6566a9ea7d1cfdaf19e791fdd7a99c291a02298f9e9434a6f75d089550028b77.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": "657c82e09ed0f6983bc40aca9642ee54bfcc154fa210b4d5b469f53c1b73799f", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8214827a2314f3d5c327783e1dba23c72006dc0ffc89b376e9cf0086edfde44b", "generation_seconds_batch": 17.056003556004725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9851582050323486, "target_z": 1.867187581466238, "ce": 5.919358730316162, "genuineness": 3.9425034523010254, "identity": 0.1915511190891266, "hypothesis": "Uh, iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge boekenkast. We zetten het naar de lunch terug.", "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/emo_Distress/657c82e09ed0f6983bc40aca9642ee54bfcc154fa210b4d5b469f53c1b73799f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "6583cba3f6c021b2c421a5b6a14c2306c74a216381fbc6b8a9bafd3b3cfd03f8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "27c59c7cb8ecbe60ccc735f525127ca124b31d2e52591aa8730db557bbb87f1a", "generation_seconds_batch": 16.022109235986136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3198001384735107, "target_z": 3.499999854158343, "ce": 5.502368927001953, "genuineness": 3.7918784618377686, "identity": 0.5906549692153931, "hypothesis": "J'ai trouvé la petite boîte. Elle était près. Elle était près. près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "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/emo_Distress/6583cba3f6c021b2c421a5b6a14c2306c74a216381fbc6b8a9bafd3b3cfd03f8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "65de4e90c1aaf995fcd66e510ab81ea1b90f043a89a89ec92ea46a78c1a99447", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "72461d93a2f32f8a34c9f8fcd42f82ea7281beb9b59e1bbb4cf4e8b3b8b24e65", "generation_seconds_batch": 23.446964450064115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15561282634735107, "target_z": -0.37109376794536014, "ce": 6.109982967376709, "genuineness": 4.7834930419921875, "identity": 0.5713867545127869, "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/emo_Distress/65de4e90c1aaf995fcd66e510ab81ea1b90f043a89a89ec92ea46a78c1a99447.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": "65fefd8966cd8f2141d784a9e2707c5572ea1bffd5ab049f8f43f4ef1c363860", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7dd611a111bcb80971976fabeea118c015f8971d5cfa4197a6b199f7cd03a90d", "generation_seconds_batch": 16.379096765071154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381488800048828, "target_z": 1.3203125780480742, "ce": 6.173524379730225, "genuineness": 4.011539936065674, "identity": 0.576912522315979, "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/emo_Distress/65fefd8966cd8f2141d784a9e2707c5572ea1bffd5ab049f8f43f4ef1c363860.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "66152423f6a806313f1d2eee99c595b004c3ff5c9c91b094db3254e8d946823e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "fcb64efa540aa10e45afd77636b4841f6a9e19a3037bb359a63dfcdf57e96878", "generation_seconds_batch": 21.074514662963338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.921299695968628, "target_z": 1.7890625393088841, "ce": 5.7247633934021, "genuineness": 4.042920112609863, "identity": 0.26175257563591003, "hypothesis": "De deur staat nog open. Ik heb je jas op de 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/emo_Distress/66152423f6a806313f1d2eee99c595b004c3ff5c9c91b094db3254e8d946823e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "6622ff1783460f1db5713724426d47bca76c0021995567b8890525dd7be9fc75", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "60a8de86adad1f7187bd64b33e21c19947d4c2e30de7476b447fa85610c6e014", "generation_seconds_batch": 23.044692018069327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08536851406097412, "target_z": -0.45703125598178673, "ce": 6.09409761428833, "genuineness": 4.570107460021973, "identity": 0.7492968440055847, "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/emo_Distress/6622ff1783460f1db5713724426d47bca76c0021995567b8890525dd7be9fc75.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "662788d8de086af7643bb37f1761e4febaf52189b15c27e345b5180ca4c049a5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "391796d020109ebcd12c9f33ef1cdf29752eed0a3da1a77e6904174889afd50f", "generation_seconds_batch": 17.208894992014393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.793582797050476, "target_z": 1.632812600835833, "ce": 6.062326908111572, "genuineness": 4.231201171875, "identity": 0.5770394802093506, "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/emo_Distress/662788d8de086af7643bb37f1761e4febaf52189b15c27e345b5180ca4c049a5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "663025ba0ebd8e7913015981a15f18faf737b01a50d9a8eb4b3d9937af702a27", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1736133175f7435969973a447217daab34cd270798059004274ade4a48ca3afd", "generation_seconds_batch": 22.07250287604984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3146440982818604, "target_z": 1.0468749304973353, "ce": 5.95112943649292, "genuineness": 4.645420074462891, "identity": 0.7266395092010498, "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/manual-comparison-v1/audio/emo_Distress/663025ba0ebd8e7913015981a15f18faf737b01a50d9a8eb4b3d9937af702a27.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "66d079642c24ddd67dfd0b3f881ad09277cd8eadceec11689bdcd17aba5e4570", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9e0ffc3df3c3f92458d59ea1dc7658ae85169c4e575b36be1f6d23c68d03bf44", "generation_seconds_batch": 23.03192246798426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30887317657470703, "target_z": -0.1835937542727048, "ce": 6.403861999511719, "genuineness": 4.319066047668457, "identity": 0.4061179459095001, "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/emo_Distress/66d079642c24ddd67dfd0b3f881ad09277cd8eadceec11689bdcd17aba5e4570.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": "677cba349c26e125bcad6041f12f56151a81607733768376551e8fcbbcc99e66", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d38a84d84f641ba3056ff268a3fba747d4d70ffe1a1a43e5cfb26d2aab92cf8e", "generation_seconds_batch": 16.659622146980837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013279438018799, "target_z": 3.1249998268130326, "ce": 6.038498878479004, "genuineness": 4.193545341491699, "identity": 0.632927417755127, "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/emo_Distress/677cba349c26e125bcad6041f12f56151a81607733768376551e8fcbbcc99e66.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "678d2d755e719335b651614c26329d8923541e2809a991382c0196d663d0aafc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1453b0c99b55d75cbcae389814302e5a571778f83593b53b246c5c8bdd1e7590", "generation_seconds_batch": 21.975962900090963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.347188264131546, "target_z": -0.13671875085454097, "ce": 6.221180438995361, "genuineness": 4.017816066741943, "identity": 0.5285886526107788, "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/emo_Distress/678d2d755e719335b651614c26329d8923541e2809a991382c0196d663d0aafc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "67a8a22357629af6f8e3536ca99f4d22db733af493f4647ea23d7bc0eb9008a3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "19cc8185fed6171ec04886f9b737dc68c8052200df9b5c4576290a0efafa239b", "generation_seconds_batch": 21.528664737939835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0771379470825195, "target_z": 3.203124868970386, "ce": 5.700935363769531, "genuineness": 3.2992093563079834, "identity": 0.5338958501815796, "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": 0.03999999999999915, "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/emo_Distress/67a8a22357629af6f8e3536ca99f4d22db733af493f4647ea23d7bc0eb9008a3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "67e7077f46d896643fb64010c29fc8c38d5884b2ac90adfc250c4235e5b37702", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "36268a2c451daf8a5a095f2ee1bca6d5b79586ed6043cc4caefe033ee9f32bdd", "generation_seconds_batch": 16.6314869140042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.247592806816101, "target_z": 0.9648438112421021, "ce": 6.0305562019348145, "genuineness": 4.394378662109375, "identity": 0.6578034162521362, "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/emo_Distress/67e7077f46d896643fb64010c29fc8c38d5884b2ac90adfc250c4235e5b37702.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "67fa646b73d0e09480c21924cddc298adffed529b05c9a83c2d09bb335102282", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f25594cb5a4f0ed8097864b96963b1bf3bb083cefed70d9ddffad15f9465e88", "generation_seconds_batch": 21.911887869006023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 5.764476776123047, "genuineness": 3.7793264389038086, "identity": 0.41651976108551025, "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/emo_Distress/67fa646b73d0e09480c21924cddc298adffed529b05c9a83c2d09bb335102282.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6810a88d536ad5af1803aca9e7654bf4b36618a0704b4c2f8e204fec96f8bb41", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b3c4f3b2093e7274da31646875e8ef670f2b733e2d5ffff63ec9d93c29aa05c3", "generation_seconds_batch": 15.97827226598747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 5.704906940460205, "genuineness": 4.193545341491699, "identity": 0.5286243557929993, "hypothesis": "La porte t'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/6810a88d536ad5af1803aca9e7654bf4b36618a0704b4c2f8e204fec96f8bb41.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "68149823d60cb6a0082126cd39956f3f2d90a3b1023a8a4dd05202e1852b6ad2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "aef21dcdae295af526c9f5f12bc24726c36163614bdba75a75f60a9a3234b214", "generation_seconds_batch": 22.47029746393673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.474290370941162, "target_z": 1.2421875358907202, "ce": 5.470598220825195, "genuineness": 4.582659721374512, "identity": 0.7011763453483582, "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/manual-comparison-v1/audio/emo_Distress/68149823d60cb6a0082126cd39956f3f2d90a3b1023a8a4dd05202e1852b6ad2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "6849a8d04516944b3a32d2fec433262e158f18d9e629859c227da845722d7d5f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c01d36fce66eb2c6fcb5ab8e9b2e32b57dfd220bcbb27be8e4f4845fa6f60bc3", "generation_seconds_batch": 23.044692018069327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14603406190872192, "target_z": -0.3828125096847975, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.68953537940979, "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/emo_Distress/6849a8d04516944b3a32d2fec433262e158f18d9e629859c227da845722d7d5f.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": "687f8deb321fb33d8f287ba1a72bda0f7513885a890eba411fed9fc5f040a012", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d56bac7a3d96dc0392ce77bcec835f50a92740c4fbd909b2c786d1dc774519f4", "generation_seconds_batch": 16.8395664509153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 4.989073753356934, "genuineness": 3.8420867919921875, "identity": 0.514447808265686, "hypothesis": "Eine Nachricht kam, als ich schon weg war. Ich las sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "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/emo_Distress/687f8deb321fb33d8f287ba1a72bda0f7513885a890eba411fed9fc5f040a012.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": "689e4c13bf28becbce90eda88fda1c3231191d295b44f27609611b87afe05eb5", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8efc760166e9bcc7b760f5acfe0665f42d892cb99d6ca44ce9a5a2891f13d102", "generation_seconds_batch": 21.442088808049448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9111058712005615, "target_z": 2.999999817697929, "ce": 4.9751739501953125, "genuineness": 3.487490653991699, "identity": 0.2984253168106079, "hypothesis": "Your message arrived after I had left. I've read it twice before putting the phone away. Let me know when we can talk.", "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/emo_Distress/689e4c13bf28becbce90eda88fda1c3231191d295b44f27609611b87afe05eb5.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": "692a85625c4cb0bd9235c7df35243ce6b2a6a8da6f05e3af6420e4495d794e55", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f240e47dd1e0154791643692a427fac34fa7bc1af3dbf8ac4b6416ed8d4c8c7d", "generation_seconds_batch": 14.941692473948933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.61354923248291, "target_z": 3.8593749897455085, "ce": 5.40705680847168, "genuineness": 3.6914620399475098, "identity": 0.5917844772338867, "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/emo_Distress/692a85625c4cb0bd9235c7df35243ce6b2a6a8da6f05e3af6420e4495d794e55.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": "69550f35ee3eafaea370d3645e147b071719088cc0c91d68e9a7859eaf00eb27", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce652246f6c9dbcc7107907d8fe44b191f1471b33b864fe56e894f318a7de893", "generation_seconds_batch": 21.585045735933818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1064891815185547, "target_z": 2.0156249282185597, "ce": 5.526196479797363, "genuineness": 3.7040140628814697, "identity": 0.5507200956344604, "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/emo_Distress/69550f35ee3eafaea370d3645e147b071719088cc0c91d68e9a7859eaf00eb27.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "69700b0ff8d4c810bf770c2adf891269cf084b1262f5df5564889935b772226f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f437921267a2e6125a20c13d747a1e6c3eabb9e0685541491bdfd630885f7ee1", "generation_seconds_batch": 22.73668335902039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3160572648048401, "target_z": -0.17480467973791963, "ce": 6.284721851348877, "genuineness": 4.545003414154053, "identity": 0.6432889103889465, "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/emo_Distress/69700b0ff8d4c810bf770c2adf891269cf084b1262f5df5564889935b772226f.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": "699bcb712782c7916c3c87b23364e9e943f76c5dcbd7ce20db6c164e70ca8d31", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a06cf2e956e90b23d1ecde346cc4b31fb3e9381680c82c6b9852045bf8a1be68", "generation_seconds_batch": 17.708016292075627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3070285320281982, "target_z": 3.4843749624001976, "ce": 5.879645347595215, "genuineness": 4.068024158477783, "identity": 0.5871948003768921, "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/emo_Distress/699bcb712782c7916c3c87b23364e9e943f76c5dcbd7ce20db6c164e70ca8d31.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "69ce14ed99a5c5a67fb9081930322bd021c6654b29f0033e079448782de1a766", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "caff2a7da1ab79f0887f13d339fcf13dc9bcb1914d400b0eddd02ce7f7650509", "generation_seconds_batch": 16.75691494497005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6592965722084045, "target_z": 0.2451172030953725, "ce": 6.133810997009277, "genuineness": 4.770940780639648, "identity": 0.5035204887390137, "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/manual-comparison-v1/audio/emo_Distress/69ce14ed99a5c5a67fb9081930322bd021c6654b29f0033e079448782de1a766.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "69da93ca929d03bddaf346765b05736785d5857e0e6a21278e1827c2b376c5e1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "99bd9acde9acbaf9ef7a0ee85ea2d487f0a11b9f63de172dbbe31c1325857e61", "generation_seconds_batch": 20.693881597951986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6664806604385376, "target_z": 0.25390627763015766, "ce": 5.9431867599487305, "genuineness": 4.607763767242432, "identity": 0.46123993396759033, "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/emo_Distress/69da93ca929d03bddaf346765b05736785d5857e0e6a21278e1827c2b376c5e1.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": "69f0117ca8d20acf41c4eeba4fa5d230f4d76bf8f759de2c0c783a2e476715a4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00c292ffda54f5ade13de0fb77ee3e69dd0752a16aafb97ad245e4c052c6e67f", "generation_seconds_batch": 16.458548591006547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.448746919631958, "target_z": 1.2109374606911159, "ce": 5.982900142669678, "genuineness": 4.042920112609863, "identity": 0.3590683043003082, "hypothesis": "Someone moved that little blue chair. It used to stand here beside the toe bookshelf. We can put it back after lunch.", "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/emo_Distress/69f0117ca8d20acf41c4eeba4fa5d230f4d76bf8f759de2c0c783a2e476715a4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "69f9397e75554686c238ac510adbe3dced349725a81526428b651b6a705ee137", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b014512d1e22f9ba697ae62f07416f9b8a9a45bd7be1c78a0b67680f51f2bbd5", "generation_seconds_batch": 15.366882481030189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8995640277862549, "target_z": 0.5390624481578485, "ce": 6.070269584655762, "genuineness": 4.118232727050781, "identity": 0.5591877102851868, "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/emo_Distress/69f9397e75554686c238ac510adbe3dced349725a81526428b651b6a705ee137.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "6a35aaea9c2ee09e29f1d9295e1d174b1c485dc6d6640ce69ab8909d9d88773f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4721e4787ed6b1d2bc71e364ee67619713694364782af46c9ba86136104ad2ff", "generation_seconds_batch": 22.358313245000318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.365730881690979, "target_z": 1.1093749350548872, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.5793634653091431, "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/emo_Distress/6a35aaea9c2ee09e29f1d9295e1d174b1c485dc6d6640ce69ab8909d9d88773f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "6a56273ad58ee09ce017a99efac6a97b07e467308c64ffde9e9e2c40f5bd5f88", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "af9534ace9f041095b41cc3abe096de7ec9715c4b714748ba080fb071c34f27d", "generation_seconds_batch": 20.663270646939054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4206255078315735, "target_z": -0.046875003418163835, "ce": 5.863759994506836, "genuineness": 4.7081804275512695, "identity": 0.6902620792388916, "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/emo_Distress/6a56273ad58ee09ce017a99efac6a97b07e467308c64ffde9e9e2c40f5bd5f88.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "7043c5d35edd504b5ec5544b53ca628accd80d020d4e1c16f4bdc5a3fefbcabe", "generation_seconds_batch": 17.09706343698781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1396482288837433, "target_z": -0.3906249920242844, "ce": 6.443574905395508, "genuineness": 4.017816066741943, "identity": 0.19765444099903107, "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/emo_Distress/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "6a8c22a6cad6e07d6af397cc50ddf669b3bdcf7447da986f988816e5ac091aad", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9ce98f91d9263143767f0f623c2b70b49956fc85654ab21c705e4fc9537bdaea", "generation_seconds_batch": 23.159329804009758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17955976724624634, "target_z": -0.3417968771363524, "ce": 6.268836498260498, "genuineness": 4.570107460021973, "identity": 0.5993208885192871, "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/emo_Distress/6a8c22a6cad6e07d6af397cc50ddf669b3bdcf7447da986f988816e5ac091aad.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": "6aa910a284855e8572c71390624119d8c21815acbd0f42c410a752e77a276b02", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "997c72968a783fb16d2da04c386b76f210e88ea501a68802184afbae01e4c28a", "generation_seconds_batch": 16.671182858990505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.37469482421875, "target_z": 2.3437499886061204, "ce": 5.736677646636963, "genuineness": 4.337893962860107, "identity": 0.6453410387039185, "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/emo_Distress/6aa910a284855e8572c71390624119d8c21815acbd0f42c410a752e77a276b02.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": "6ab716fafa6faa2863ac6099819c91b9215c2f5649abe8991cdc5478de814a0e", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b8a59b0868dbf928c6cc22cbbd85ec3ee8e78985afc1fe0d0ad4ab5d0b342816", "generation_seconds_batch": 17.177851804997772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3874664306640625, "target_z": 2.359374880364266, "ce": 5.502368927001953, "genuineness": 3.760498285293579, "identity": 0.386726438999176, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche 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/emo_Distress/6ab716fafa6faa2863ac6099819c91b9215c2f5649abe8991cdc5478de814a0e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6ac1589e023a12569bd7b9d5a814ce23f335705f6222106dcd2f750777e45fc3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b7b59d3564e69aff4e1068c10319ebbe427525bd2f8333d576ec6aa608008206", "generation_seconds_batch": 15.97827226598747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6007773876190186, "target_z": 3.843749806304049, "ce": 5.704906940460205, "genuineness": 3.7291181087493896, "identity": 0.6942968368530273, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. 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/emo_Distress/6ac1589e023a12569bd7b9d5a814ce23f335705f6222106dcd2f750777e45fc3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "6ad098e0ae7a392e140b22adba1fb61bb74dd5b4d503f7522c7c44c1d324749e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2c348c721007111e29d384a324ac0e82127b2ada6b658df26dd20dc5468fb95b", "generation_seconds_batch": 17.2802964260336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7542860507965088, "target_z": 0.3613281376756909, "ce": 5.919358730316162, "genuineness": 4.519899368286133, "identity": 0.48297134041786194, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/6ad098e0ae7a392e140b22adba1fb61bb74dd5b4d503f7522c7c44c1d324749e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "6b6118495f759ebf78927c7a3588bd838918791df7f878c0cc5d4afb8cf84763", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "347c5ffe6d33db16d4e10c80d01b84462b4826fc2c6dd3cc86fb908ab64af173", "generation_seconds_batch": 21.04007206298411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2214343547821045, "target_z": 2.1562498290918084, "ce": 5.685050010681152, "genuineness": 4.2249250411987305, "identity": 0.6849831342697144, "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/emo_Distress/6b6118495f759ebf78927c7a3588bd838918791df7f878c0cc5d4afb8cf84763.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "ff1164f989ea2a62756facb3bbe788cc83e5bd4cbb1c8dbb85b2fa72c56742ee", "generation_seconds_batch": 16.843687422922812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19712084531784058, "target_z": -0.32031250512724574, "ce": 6.197352409362793, "genuineness": 4.758388519287109, "identity": 0.6553300619125366, "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/emo_Distress/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "6bc79f17d4484bec34589e20c5633de81df95fea5e8373512d91630ec92fe559", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "89038094caca0c34ac0ab7000f1ee80ba130edc5d883bf9b1e3ebdf4af4b68e0", "generation_seconds_batch": 17.038579487008974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3902927339076996, "target_z": -0.08398437656665843, "ce": 6.23706579208374, "genuineness": 4.231201171875, "identity": 0.5778095722198486, "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/emo_Distress/6bc79f17d4484bec34589e20c5633de81df95fea5e8373512d91630ec92fe559.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "6bd5b01386d5c3b71ec1e04eadd65a87c1732794390af0e520461d6fcdaad262", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2bb682ce95597a640400a20b1631e34a7755f17c7a4c05edef5bc50fb8a66e9a", "generation_seconds_batch": 17.185673156986013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5700781345367432, "target_z": 1.3593750991267513, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.41520118713378906, "hypothesis": "Ik heb een klein doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "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/emo_Distress/6bd5b01386d5c3b71ec1e04eadd65a87c1732794390af0e520461d6fcdaad262.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6beb603604dd2a025b535bd92f9a349b7f75b20e7da25ba444fa0d601a02c14c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ff8acb29333dab2476dd23612214e92093ca5e050eb4b4eadc5f3aece1fff109", "generation_seconds_batch": 22.000364835956134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1958911418914795, "target_z": 2.1250000455755176, "ce": 5.855817794799805, "genuineness": 4.570107460021973, "identity": 0.5740556716918945, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. C'est prégénie.", "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/emo_Distress/6beb603604dd2a025b535bd92f9a349b7f75b20e7da25ba444fa0d601a02c14c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "6c1e5bb9f6e26766c4b2a17bee38bf92b0569d3c4bbfe88f283061c15d622e13", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "646a3e5c3d71ce935a5a84d47c03014ebd1428494fe4974e6c600f8a5b3ccbd5", "generation_seconds_batch": 18.994405148085207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1537680625915527, "target_z": 3.2968748028858856, "ce": 5.7406487464904785, "genuineness": 4.030367851257324, "identity": 0.46744266152381897, "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/emo_Distress/6c1e5bb9f6e26766c4b2a17bee38bf92b0569d3c4bbfe88f283061c15d622e13.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6ca66dc38d3a5d514d1c2b09bfae872fd45943306899d9d3cd83384b46e84ef7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4ba5cde30bdd85a085f7c274d795d9b2f7796ade71d1b0323a917271668f7b87", "generation_seconds_batch": 21.48531643592287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7383214235305786, "target_z": 0.3417968771363524, "ce": 6.0146708488464355, "genuineness": 4.607763767242432, "identity": 0.6922523379325867, "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/emo_Distress/6ca66dc38d3a5d514d1c2b09bfae872fd45943306899d9d3cd83384b46e84ef7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "6d072aa9318616f948a906605cef4c2e378fbf0ebfc51a748175c2568eee6390", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "049cc83d90fee00b7fb970465746b403dbda9ed7fb0d569529ceea16dadd356e", "generation_seconds_batch": 24.36039050796535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8995640277862549, "target_z": 0.5390624481578485, "ce": 5.998785495758057, "genuineness": 4.105680465698242, "identity": 0.6416816115379333, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, waar staan 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/emo_Distress/6d072aa9318616f948a906605cef4c2e378fbf0ebfc51a748175c2568eee6390.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "6d0f3bf4a13c4012106ca3a0f329ef15322d7e27b4212b06ddf4373d6e9d285b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8228c8288c3e0af58e9b8ffaf465f1dcb3834ca22454cd095703b769c6906446", "generation_seconds_batch": 21.562189968070015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2003137767314911, "target_z": -0.3164062457272952, "ce": 6.205295085906982, "genuineness": 4.193545341491699, "identity": 0.3259403109550476, "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/emo_Distress/6d0f3bf4a13c4012106ca3a0f329ef15322d7e27b4212b06ddf4373d6e9d285b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "6db00de81e4c16417c2135a58f5e6501e97b579d2b9664bf7818ab62ec3f2937", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3e207386a163c4a00c23fdad69e366a266428832385770ff45a7ab5e6631354d", "generation_seconds_batch": 21.323935832013376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6433319449424744, "target_z": 0.225585942556034, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.6146466732025146, "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/emo_Distress/6db00de81e4c16417c2135a58f5e6501e97b579d2b9664bf7818ab62ec3f2937.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": "6ed383c80a0157b59453fab25b1d0a95c682485c5a57d239160b98755d8d05a4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac06c719b3942d422c19d73d359ca809c5d2edfe88f2dc5a481147404ac8d204", "generation_seconds_batch": 16.8395664509153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.779581069946289, "target_z": 4.062499749334652, "ce": 5.125091552734375, "genuineness": 3.575355052947998, "identity": 0.46467873454093933, "hypothesis": "Deiner Nachricht damals ich schon weg war. Ich lasse sie zweimal. Dann leg dich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.25, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/6ed383c80a0157b59453fab25b1d0a95c682485c5a57d239160b98755d8d05a4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "6f2c3b4acd249e7b3568fba3fba9b9b85be6dbfa46e86d3a89fe5a982a935cb4", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "61f26a7ec862482e7f9964d2dd49adb10fd08df61ecab2e602dc1d815d8d33d8", "generation_seconds_batch": 13.995535591966473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40545913577079773, "target_z": -0.06542967176220402, "ce": 5.839932441711426, "genuineness": 4.3504462242126465, "identity": 0.6853446960449219, "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/emo_Distress/6f2c3b4acd249e7b3568fba3fba9b9b85be6dbfa46e86d3a89fe5a982a935cb4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6f4a670b4035955be3ee44bebc8f4c4e0e5136befdddb13d5fada1699486b339", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "22d6b0649d668e264f2e85171189540115b967e57ad2b69b168dc64892a23c6d", "generation_seconds_batch": 15.733237804030068, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.872790813446045, "target_z": 2.953124850740179, "ce": 5.824047088623047, "genuineness": 4.105680465698242, "identity": 0.607446551322937, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu aurais prêt.", "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/emo_Distress/6f4a670b4035955be3ee44bebc8f4c4e0e5136befdddb13d5fada1699486b339.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": "6f5e587e17055652b28c5d8637ec47c79dc075cfd75abc936169ad330f741d2e", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8fda31a8337402b4e75ca240613333a05ba909df0b8004ebbb8d81c544f3ac7", "generation_seconds_batch": 21.978102955035865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.77639102935791, "genuineness": 3.9173994064331055, "identity": 0.4731467366218567, "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/emo_Distress/6f5e587e17055652b28c5d8637ec47c79dc075cfd75abc936169ad330f741d2e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "6f98306d0e55b85514bf52863e212f6d3072a89d60c00af2daf89aa0c4f78d02", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "86cc80de6b73e9dfcff8b5e4a6cd4d3c44a7f6325e0fc5902d44959f02585104", "generation_seconds_batch": 18.839293269906193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0260512828826904, "target_z": 3.1406250102544915, "ce": 5.331601142883301, "genuineness": 3.961331605911255, "identity": 0.3786838948726654, "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/emo_Distress/6f98306d0e55b85514bf52863e212f6d3072a89d60c00af2daf89aa0c4f78d02.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "6fbfe45072356ce722b9b1fa9c513b59ba4215d456e6e3bb3a59ffd9d5dd55ef", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "583c32151d5ba0cafdc59379f05100e5e9e7d1cd27792c8f918d4af3094751cd", "generation_seconds_batch": 24.18006433802657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2553917169570923, "target_z": -0.24902342603490882, "ce": 5.998785495758057, "genuineness": 4.344170093536377, "identity": 0.5992439985275269, "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/emo_Distress/6fbfe45072356ce722b9b1fa9c513b59ba4215d456e6e3bb3a59ffd9d5dd55ef.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "700943e3755f7a96cad97b9d87d984b26db0895740ac7d910b340048f2f56917", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e1b1fc6dd2544657da1f7b6aba90f802cea65a56ae21aec9aa3a2aafc4f4bb0a", "generation_seconds_batch": 23.227101668016985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6840417385101318, "target_z": 0.2753906496392643, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.4880978465080261, "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/emo_Distress/700943e3755f7a96cad97b9d87d984b26db0895740ac7d910b340048f2f56917.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "707cce71b4ea9ee7b4c1e0c872666bbad343f2122a5bb4db8f4bcaa37db35fdb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1d899258ddc23c62cd80b3137a009336590c97e971bac86016dd97830a9cf12f", "generation_seconds_batch": 21.626170224044472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6646358966827393, "target_z": 3.921874848461403, "ce": 5.871703147888184, "genuineness": 4.036643981933594, "identity": 0.4226534962654114, "hypothesis": "Die Tür, die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/707cce71b4ea9ee7b4c1e0c872666bbad343f2122a5bb4db8f4bcaa37db35fdb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "707d882faf2e638cbeeefbe0c15aea1f4c9e87a2470eae6963ee06c8ba159800", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ebb7a5eed2a7a117d5dc14ebc3d13f658fcb92204f7d0afabff860b0a24047c1", "generation_seconds_batch": 17.32784017897211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09654375910758972, "target_z": -0.44335936631216694, "ce": 6.213237762451172, "genuineness": 4.7081804275512695, "identity": 0.6250876188278198, "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/emo_Distress/707d882faf2e638cbeeefbe0c15aea1f4c9e87a2470eae6963ee06c8ba159800.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "707dc61b88d33df57608130599596f234ee3168057484f8ca373efc551b132c8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ee4845c55b9e1c0724d3703e4ce6517bb5f53a397935501099b931c4eaa12c69", "generation_seconds_batch": 16.74752983392682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6401389837265015, "target_z": 0.22167964669566922, "ce": 6.062326908111572, "genuineness": 3.9550557136535645, "identity": 0.5919114947319031, "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/emo_Distress/707dc61b88d33df57608130599596f234ee3168057484f8ca373efc551b132c8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "7126a575c8a8a9c6f6114477278436abb65459d46be382a05357dd53df893911", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "839ffb8f68449729e17acb9b3bde61041ded077ec516253bf1af0c69c481f561", "generation_seconds_batch": 20.45624362595845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7424960136413574, "target_z": 1.5703125962782813, "ce": 5.80021858215332, "genuineness": 4.482243061065674, "identity": 0.5514275431632996, "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/emo_Distress/7126a575c8a8a9c6f6114477278436abb65459d46be382a05357dd53df893911.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "72609e23c9c5a0378f7c21d970f310fb9588369afac275a9e65d72ce6b990ee3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d2e57b924b4e3551e947b903655522584594b7a277f8a8218012783cfa44ce1d", "generation_seconds_batch": 13.697948400047608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 6.0146708488464355, "genuineness": 3.7416701316833496, "identity": 0.5629882216453552, "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": 0.03999999999999915, "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/emo_Distress/72609e23c9c5a0378f7c21d970f310fb9588369afac275a9e65d72ce6b990ee3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "7261d3616b674332c85422f2a82da5294b2c83fbe472a88499bba947cefd1563", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4397b90bf06e93a5ddebdf97ec9f97748aaab69364950047bdeafd1e80c7561c", "generation_seconds_batch": 21.75186994089745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.642900228500366, "target_z": 2.6718747573103676, "ce": 5.808161735534668, "genuineness": 4.143336772918701, "identity": 0.4860478937625885, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/7261d3616b674332c85422f2a82da5294b2c83fbe472a88499bba947cefd1563.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": "728982e9afe8f98f88fe59c7d40a8e3707e6bc8bbba8d5f4188c07e96d36d36b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9148f202549e2f7a08422afc2dc6cb2fc10c78a3ecf75ce7ccd34f49b701c9c", "generation_seconds_batch": 16.860703871003352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0490164756774902, "target_z": 1.945312331940278, "ce": 6.205295085906982, "genuineness": 4.632867813110352, "identity": 0.581490159034729, "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/emo_Distress/728982e9afe8f98f88fe59c7d40a8e3707e6bc8bbba8d5f4188c07e96d36d36b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "732c3f270c56d2e7a00f09a8a547c1bc81f17b35e8575069edbad49278150632", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "06750c7406bdfb46d52fa9a0ef1b535bc213b3ccf0bfac6c7051d165e3a3e807", "generation_seconds_batch": 22.56506997696124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27375102043151855, "target_z": -0.2265624982909181, "ce": 6.086154937744141, "genuineness": 4.595211505889893, "identity": 0.4982544779777527, "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/emo_Distress/732c3f270c56d2e7a00f09a8a547c1bc81f17b35e8575069edbad49278150632.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "7344a7e53ad9d1599defd96b2bb42fe0e61bd2978412f6739feff2d2fc93a91e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "78ad67c2221659ad9be730a6235f55174f09ec948aa6d591d03ddae811a40ce7", "generation_seconds_batch": 21.816190349985845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.38003396987915, "genuineness": 4.645420074462891, "identity": 0.6135062575340271, "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/emo_Distress/7344a7e53ad9d1599defd96b2bb42fe0e61bd2978412f6739feff2d2fc93a91e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "73ca24599f8b68c30b1953784cd7bc81a6ec930676fd52ab23502b97e6d49a19", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d9ba5f16ee735ef3d7d0e26d7288b925565f66549bb5fbfa1534e9bf9ec1b252", "generation_seconds_batch": 22.799022796098143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4640965461730957, "target_z": 2.453124814279765, "ce": 4.940424919128418, "genuineness": 3.848362922668457, "identity": 0.6654223203659058, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête à la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/emo_Distress/73ca24599f8b68c30b1953784cd7bc81a6ec930676fd52ab23502b97e6d49a19.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "7409293d77a3054baa3a22973f404e82656c4716d0794209ceb69db6f0f78614", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "0f7b2dfdc382b542971562d02dd02d36868d41648d15f3cf6690d8ebebaf3f18", "generation_seconds_batch": 23.281363464077003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8817546367645264, "target_z": 4.187499758449755, "ce": 5.3792572021484375, "genuineness": 3.603597402572632, "identity": 0.5513468980789185, "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/emo_Distress/7409293d77a3054baa3a22973f404e82656c4716d0794209ceb69db6f0f78614.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "74175b254fd547921f358ef2c61fe98405ba5456d4e823f4a44f4d9e3280fa8a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c73fd87e0a514832740a3ccf7ffcfdf59433fc040bad5283d0f41eda74a35731", "generation_seconds_batch": 22.107084238901734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4347453117370605, "target_z": 3.6406247550315918, "ce": 5.015880107879639, "genuineness": 3.512594699859619, "identity": 0.6423065662384033, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/74175b254fd547921f358ef2c61fe98405ba5456d4e823f4a44f4d9e3280fa8a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "743b4ab44d673e4b50ec24f020d48b7e202097740f063b33320c7929ed2b39bf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "39f36b228caecf456350211f9a83549fb5f36a48afe58bf11335f91bd06ad237", "generation_seconds_batch": 22.031475202995352, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11410483717918396, "target_z": -0.4218749943030603, "ce": 6.2767791748046875, "genuineness": 4.7458367347717285, "identity": 0.5887211561203003, "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/emo_Distress/743b4ab44d673e4b50ec24f020d48b7e202097740f063b33320c7929ed2b39bf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "7475a2c3336c8430e22b94d4511bd2b8c7bec54f23dd71009670d7f109224dba", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "dc5970db4866b945f98ea72bc98391d7413450510aa64ec5caf2130431417437", "generation_seconds_batch": 20.67907530395314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 5.5817952156066895, "genuineness": 3.5220088958740234, "identity": 0.231354221701622, "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": 0.03999999999999915, "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/emo_Distress/7475a2c3336c8430e22b94d4511bd2b8c7bec54f23dd71009670d7f109224dba.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "74d0de592aac98c423375580bfddb93bac0244ca4ef8a53be1ab2e2fcef78dce", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f9db06afcd8a935a265f08a99ed67436f3c3e77d0d7efc9c797613aa68a74a69", "generation_seconds_batch": 22.542745109065436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2913120985031128, "target_z": -0.20507812628181143, "ce": 5.7128496170043945, "genuineness": 4.570107460021973, "identity": 0.7187837362289429, "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/emo_Distress/74d0de592aac98c423375580bfddb93bac0244ca4ef8a53be1ab2e2fcef78dce.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": "750b529ba379b3ded572d728dc5bca933ccaa1c1581aedb25f168db2dd0bd878", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a8b86212f639923b383bf16bbe3f4a3004e333c312cb70fee9ba977d767958dd", "generation_seconds_batch": 16.97468567197211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4896399974823, "target_z": 2.484374889479369, "ce": 6.372091293334961, "genuineness": 4.2751336097717285, "identity": 0.6239035129547119, "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": 0.03999999999999915, "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/emo_Distress/750b529ba379b3ded572d728dc5bca933ccaa1c1581aedb25f168db2dd0bd878.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "759f7d4f04640691d210eebd2165c84fc9de8f0a87b0e93e9db72386702ddfb3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2afc8d7205070156224d8256d46aeec6a2b03a157b78cf913933fd9ca62d2782", "generation_seconds_batch": 21.12814907496795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09494727849960327, "target_z": -0.4453125142423493, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.42017847299575806, "hypothesis": "¡Te he encontrado! La cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/759f7d4f04640691d210eebd2165c84fc9de8f0a87b0e93e9db72386702ddfb3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "767e37af74ba4220f040745988105def92ae64d598f8a3de1b31e4ad3c345231", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d739f7a5d397fbe3202d6acf550d09a07d2a82470b1ed0a7b1b3a80c798867f", "generation_seconds_batch": 17.05008179601282, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0005078315734863, "target_z": 3.109374935054887, "ce": 5.927301406860352, "genuineness": 3.998987913131714, "identity": 0.6762423515319824, "hypothesis": "Ich hätte die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "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/emo_Distress/767e37af74ba4220f040745988105def92ae64d598f8a3de1b31e4ad3c345231.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "769612db5a7406367223779ca4170b6b44ce42c4ad7bad8f90615c1f48e079ab", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "93c284d172728ab12173956a2a70ed021f79d69b772157d5da60340f099c57ae", "generation_seconds_batch": 22.916819524019957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19712084531784058, "target_z": -0.32031250512724574, "ce": 6.213237762451172, "genuineness": 4.582659721374512, "identity": 0.6796606779098511, "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/emo_Distress/769612db5a7406367223779ca4170b6b44ce42c4ad7bad8f90615c1f48e079ab.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "722c2efaa3af073c7f829c887c9aee4959c59b4e70c0be97faa59a6883631649", "generation_seconds_batch": 16.858448659069836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12368360161781311, "target_z": -0.41015625256362287, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.6909995079040527, "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/emo_Distress/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "783f45953c230d989728a3c8d9304ca5896a2b206fc54a82a6f301f61bb971e6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bbb7f71fc06f2566bfc1672ec0ddd6c7027ba30e0459f81170e612935e4a3f2e", "generation_seconds_batch": 19.08477616601158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.039708137512207, "genuineness": 3.5314228534698486, "identity": 0.4245383143424988, "hypothesis": "La puerta sigue abierta. He dejado. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/783f45953c230d989728a3c8d9304ca5896a2b206fc54a82a6f301f61bb971e6.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": "791c0146bb0c482358260082bc46cfbeb965347d69f38499d527079845aba3c5", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd59b1afae7d3da303dc4ced5eaf0ccbccd443427eda8932ef268441a92af5d5", "generation_seconds_batch": 21.869606247986667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7961606979370117, "target_z": 2.85937491682468, "ce": 5.442798614501953, "genuineness": 3.8169827461242676, "identity": 0.6553612947463989, "hypothesis": "J'écris le numéro sur l'enveloppe, le bien, et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/791c0146bb0c482358260082bc46cfbeb965347d69f38499d527079845aba3c5.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "cf50a245bfd33bb0a0333449c34ac76d318817121cb74c427ec4053c7417f7ba", "generation_seconds_batch": 13.708990516955964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.727155327796936, "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/emo_Distress/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "7980d978d56d454844335456502ef0359ae176e6a9f48ca35c9eb80775bb9cff", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "185bc8e863dfa7c31b787efb5830ef1e8ddbbb7e9edcfc2c94375f773e328199", "generation_seconds_batch": 20.23061308299657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3018724918365479, "target_z": 1.03125003873919, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.8042203187942505, "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/manual-comparison-v1/audio/emo_Distress/7980d978d56d454844335456502ef0359ae176e6a9f48ca35c9eb80775bb9cff.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "7a14294e8250326526321d198d81c4719e607a2c01d042a66d991c1a10fbbac3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b7b723861cfbef2f2039ceff6304a82a06c6844676019c2fe4fc7f9b4883d2ac", "generation_seconds_batch": 19.231430392945185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6211649179458618, "target_z": 1.421875103684303, "ce": 5.959072113037109, "genuineness": 4.042920112609863, "identity": 0.5852822661399841, "hypothesis": "I found l 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/emo_Distress/7a14294e8250326526321d198d81c4719e607a2c01d042a66d991c1a10fbbac3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "7a5a538ce3042e849a2d5e225250809dfbd69ec19cee1352ed77fd473e5fbbad", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6d6e6a318ccae509d915124ff5ee9044c6de37840d4e234afc88c204379b057d", "generation_seconds_batch": 22.865615687100217, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11250835657119751, "target_z": -0.42382814223324267, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7037613391876221, "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/manual-comparison-v1/audio/emo_Distress/7a5a538ce3042e849a2d5e225250809dfbd69ec19cee1352ed77fd473e5fbbad.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "7ba6b5e8802428a029ee673cfd54117dbfb64dccab3d0e64e83f8e34b86e7bd7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ba0e45aeeb9cbd5afc54b1f39b7a0609d91e6e9932fe0cb43238c7c979172d39", "generation_seconds_batch": 21.973066508071497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.038822889328003, "target_z": 3.156249902012637, "ce": 6.086154937744141, "genuineness": 3.8922953605651855, "identity": 0.18090981245040894, "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": 0.03999999999999915, "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/emo_Distress/7ba6b5e8802428a029ee673cfd54117dbfb64dccab3d0e64e83f8e34b86e7bd7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "7bbd00fa7c0935d0aea25b16f12205805e08b9dd618418a459b692a788b96862", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "7ad6237981d4c27cb3d14768b8c0b316d20eba85f46e9c37be55bc2430ec70db", "generation_seconds_batch": 15.39896497700829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.642900228500366, "target_z": 2.6718747573103676, "ce": 5.998785495758057, "genuineness": 4.519899368286133, "identity": 0.48214346170425415, "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/emo_Distress/7bbd00fa7c0935d0aea25b16f12205805e08b9dd618418a459b692a788b96862.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "7c0fc4bcc05675999a16a4d9aeb3f490be7d1d541e764e9eb2a031414c760559", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ba449db43c169e7967e1dd423652afd3aa9cac7d8ae5fbf5fe76bbaaadcb8318", "generation_seconds_batch": 24.38180191302672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5024116039276123, "target_z": 2.4999997812375145, "ce": 6.0146708488464355, "genuineness": 4.394378662109375, "identity": 0.4676975607872009, "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/emo_Distress/7c0fc4bcc05675999a16a4d9aeb3f490be7d1d541e764e9eb2a031414c760559.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "7c1cb783def464c447666daf625c81d328c2fb71c8ee0cda7fda99c0ed94c6bc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b5951d9030c7e444c924aaf2e837c0e94f34c500259339e13ee60cb467a1424d", "generation_seconds_batch": 22.06757870898582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4640965461730957, "target_z": 2.453124814279765, "ce": 5.903473377227783, "genuineness": 3.6663577556610107, "identity": 0.5076531767845154, "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/emo_Distress/7c1cb783def464c447666daf625c81d328c2fb71c8ee0cda7fda99c0ed94c6bc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "7d09632b52b30472099c92018ca30f309bfd9946dad7b96c7ba8050ae967c594", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e12b0a45f162ca6cdd491901432ff56527b94d793f8ef2eb42b6fe1170f52e0f", "generation_seconds_batch": 15.343514309031889, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1651916205883026, "target_z": -0.3593749897455085, "ce": 6.109982967376709, "genuineness": 4.7458367347717285, "identity": 0.6379146575927734, "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/emo_Distress/7d09632b52b30472099c92018ca30f309bfd9946dad7b96c7ba8050ae967c594.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": "7d8bf96db784752010b8efe63f2352e4bd981ab54147126542d5abe9da99d2bc", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee786d6d580ff453bb9e35b858c6fb2e8177cea3111d0567140690907c1d1826", "generation_seconds_batch": 15.136669531930238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2539786100387573, "target_z": 0.9726562571211746, "ce": 5.863759994506836, "genuineness": 4.030367851257324, "identity": 0.589932382106781, "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/emo_Distress/7d8bf96db784752010b8efe63f2352e4bd981ab54147126542d5abe9da99d2bc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "7dab41760fd97629718fbaf7401f909ef24334a0a5b3e30dec1ccb0fadaec41a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dae609bdc27d2a4ee2607be92d351eca2bab6816a1b7ccb14491f5de44c08cb9", "generation_seconds_batch": 20.862136048963293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14603406190872192, "target_z": -0.3828125096847975, "ce": 6.435632705688477, "genuineness": 4.469690799713135, "identity": 0.6621260643005371, "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/emo_Distress/7dab41760fd97629718fbaf7401f909ef24334a0a5b3e30dec1ccb0fadaec41a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "7dc4aeeea1ef2a0fc422906f128ae55e3c9b83d29c35dc01685b47754ad12ede", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "fa64c1ae73347546a726f665023c45b619798f5f040caab1a6e1df128d618d45", "generation_seconds_batch": 20.505957223009318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2597496509552, "target_z": 2.2031250877328716, "ce": 5.847874641418457, "genuineness": 3.9801597595214844, "identity": 0.5785892009735107, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen 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/emo_Distress/7dc4aeeea1ef2a0fc422906f128ae55e3c9b83d29c35dc01685b47754ad12ede.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "7def3af65fa3dcfc22a5adbc616dadb9255a79c3ca52fb094c161f6c5d50380b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6dc583ba48e29996e7e880498331f5766b30e951eb244d61daec1ede64de9c43", "generation_seconds_batch": 22.87724204303231, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984098553657532, "target_z": 0.29296872578800615, "ce": 6.078212261199951, "genuineness": 4.218649387359619, "identity": 0.43737900257110596, "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/emo_Distress/7def3af65fa3dcfc22a5adbc616dadb9255a79c3ca52fb094c161f6c5d50380b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "7df8a33f0647a96f5dc179831b929ad2eae5cc34af9f36695c7e5838aa724712", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6483ab57c91d2c21a81d5b05226158b3e4ed9ac55d81d140a3c409ea879c8ba8", "generation_seconds_batch": 21.10813823796343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23703239858150482, "target_z": -0.27148437200910663, "ce": 6.23706579208374, "genuineness": 4.337893962860107, "identity": 0.5319863557815552, "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/emo_Distress/7df8a33f0647a96f5dc179831b929ad2eae5cc34af9f36695c7e5838aa724712.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "7e0024f4cdfa3edfbe2ffd732710f747ac024ae85073b8936af1d6911cce763e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a4f7886218943dfe76fc952bbe2079b94796bd354f7bf46fb865af8d8333a01f", "generation_seconds_batch": 21.098321545054205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18754208087921143, "target_z": -0.33203124686668317, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.616297721862793, "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/emo_Distress/7e0024f4cdfa3edfbe2ffd732710f747ac024ae85073b8936af1d6911cce763e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "7f247599f6bd09220de571bb30d28b779743fdf7b5251c30d6701d0492fa6ede", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bb2fc385092f96c18b3f04a332bae659ebf0960f2ba652286c3b3c192ddbaccf", "generation_seconds_batch": 22.591464730910957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0464385747909546, "target_z": 0.7187500159514312, "ce": 5.974957466125488, "genuineness": 4.124508857727051, "identity": 0.44221413135528564, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dice, lindo, faina al zar, dime cuándo estás listo. Do pizza voy en Percy con esto. La es puerta.", "wer": 1.0, "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/emo_Distress/7f247599f6bd09220de571bb30d28b779743fdf7b5251c30d6701d0492fa6ede.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": "7f4f8ae13a4628e20d4f0f81a37e4baf04fb6cbaf4ddf1e56307bde9aaa1085c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "137b9869eedfe33304f1bd6971cc41b84e736c727d5749ef18ef65b1e5c24279", "generation_seconds_batch": 22.432491926010698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.08610200881958, "target_z": 4.437500068363277, "ce": 5.585766792297363, "genuineness": 3.7542223930358887, "identity": 0.6115208268165588, "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/emo_Distress/7f4f8ae13a4628e20d4f0f81a37e4baf04fb6cbaf4ddf1e56307bde9aaa1085c.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "2204a37c5d070bc6dcdcbd19c1968b841044d9320075977f119b93842540d81d", "generation_seconds_batch": 14.933972772094421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.443574905395508, "genuineness": 4.494794845581055, "identity": 0.4474669396877289, "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/emo_Distress/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "7fb1d376e47dc5edfa396db0b1f477b1cab425f326380fbf84badf0d29dc64d0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "47309f9e9b3aa1682e4b0014dae3fb71f10f7c02069179addb350b92d7ff82f2", "generation_seconds_batch": 21.421208717045374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.805124521255493, "target_z": 4.093749824534257, "ce": 5.522225379943848, "genuineness": 3.3494176864624023, "identity": 0.14575836062431335, "hypothesis": "De sleutels, de lighond op de keukentafel. Ik... In de draam. Neem ze mee als je weggaat!", "wer": 0.4090909090909091, "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/emo_Distress/7fb1d376e47dc5edfa396db0b1f477b1cab425f326380fbf84badf0d29dc64d0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "7ff2aed0d192fe29df46f6e5cf99a23df4afece0bf10e1af72df9d68d659f2ac", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dbbf86d9332193a583ff0308e50c4f6939918e0a19abf8e52902e91ca336a616", "generation_seconds_batch": 14.845030892058276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9123357534408569, "target_z": 0.5546874857576507, "ce": 6.181467056274414, "genuineness": 4.645420074462891, "identity": 0.7666205167770386, "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/emo_Distress/7ff2aed0d192fe29df46f6e5cf99a23df4afece0bf10e1af72df9d68d659f2ac.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "8972024d0dbeb5daece55079e4a2a63c7f5437ec2ba5471292c15d287ad6629e", "generation_seconds_batch": 17.567081885994412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1396482288837433, "target_z": -0.3906249920242844, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.6676342487335205, "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/emo_Distress/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "818947a10472701119f8fdfe4ec314021d69429e618217172da45abccbd68ab8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d38a7e74be951485866be4d2a115e549f2f51bec9bb7cdc82b9e4ae806bc2219", "generation_seconds_batch": 23.730859798029996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226642370223999, "target_z": -0.28906250284846985, "ce": 6.332377910614014, "genuineness": 4.3881025314331055, "identity": 0.3081672787666321, "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": 0.03999999999999915, "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/emo_Distress/818947a10472701119f8fdfe4ec314021d69429e618217172da45abccbd68ab8.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": "81b3fb8b185662cf0dc0d1a02c8fead0f28b1e6f35418d4486440518a001377b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4662b9ecf3980c22f267b924bf43b9d60b321e1e7f6660f1a401f5a7d53f5a20", "generation_seconds_batch": 16.001855536014773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7450737953186035, "target_z": 2.7968747664254714, "ce": 6.252951145172119, "genuineness": 3.71028995513916, "identity": 0.31915920972824097, "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/emo_Distress/81b3fb8b185662cf0dc0d1a02c8fead0f28b1e6f35418d4486440518a001377b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "81dd436b3b91416f30dfe4fdfcd7f2f818166e870cccba736304e3ac85256336", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f22eb0fdcde2f409c0025c0a7c11253bde61c9853dd34d4e75fecf33e4b21b97", "generation_seconds_batch": 22.058213534997776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.617357015609741, "target_z": 2.6406249737940772, "ce": 5.784333229064941, "genuineness": 4.13078498840332, "identity": 0.5804802179336548, "hypothesis": "J'ai trouvé la petite boîte. Elle était prêt, petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle 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/emo_Distress/81dd436b3b91416f30dfe4fdfcd7f2f818166e870cccba736304e3ac85256336.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "8204cb76cba8984c0fd077f22eb1a64bbb3480d4575ee8b402c9cf921ef7df2e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f2e0ab1a8282441e5eca6584329e0ca2dac909094d0454bb4b663d30b93bd8db", "generation_seconds_batch": 22.36436681204941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5126054286956787, "target_z": 1.28906250284847, "ce": 6.125868320465088, "genuineness": 4.168440818786621, "identity": 0.3734965920448303, "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/emo_Distress/8204cb76cba8984c0fd077f22eb1a64bbb3480d4575ee8b402c9cf921ef7df2e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "8279f29be4813b9f372deaf886ad4b6aa51f22de40e340fa20189f5da188caa9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d15acd73dadc781b905da506bbd3fbd6c6c2b22315beea77264503224ffdf0e9", "generation_seconds_batch": 22.52061407698784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9761942625045776, "target_z": 0.6328125279150046, "ce": 5.863759994506836, "genuineness": 4.143336772918701, "identity": 0.5075366497039795, "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/emo_Distress/8279f29be4813b9f372deaf886ad4b6aa51f22de40e340fa20189f5da188caa9.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": "82962e6a9f46c99541f00680b9f6c6122afba8dcb7baf900aadc9aa52a7ebbe6", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "404a92fb27912ee3c437a54222a4a4ef7789138ea46a14e241030ccd8f11ba32", "generation_seconds_batch": 15.085787373012863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0260512828826904, "target_z": 3.1406250102544915, "ce": 5.303802013397217, "genuineness": 3.7667744159698486, "identity": 0.5340648889541626, "hypothesis": "Ils sont sur la table de la cuisine. J'ai incardé dans le tiroir, puis près de la fenêtre. Prends les gars, tu partiras.", "wer": 0.16666666666666666, "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/emo_Distress/82962e6a9f46c99541f00680b9f6c6122afba8dcb7baf900aadc9aa52a7ebbe6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "82c6eb738e500757c7194e54e339cfc1f9d5ded7e1dbda95084d43a9849442ce", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "3c7612201d6fd43d8c05321ecce0cf0ca57d3643d8697a67eeca99d0e8931d0a", "generation_seconds_batch": 23.053550151991658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984098553657532, "target_z": 0.29296872578800615, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.5796381235122681, "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/emo_Distress/82c6eb738e500757c7194e54e339cfc1f9d5ded7e1dbda95084d43a9849442ce.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "83594297d9d8e66c977f5a03c5ed21e6e25e6900e0c540a32224ba7bddd14535", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "807e5f1dd86f8f0571c02f04c7fd819c94d1be596abf7832ade0ed0c88d4efa9", "generation_seconds_batch": 23.082730310969055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8574411869049072, "target_z": 1.71093749715153, "ce": 5.355429172515869, "genuineness": 4.218649387359619, "identity": 0.7052188515663147, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Et moi, quand tu es prêt ?", "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/emo_Distress/83594297d9d8e66c977f5a03c5ed21e6e25e6900e0c540a32224ba7bddd14535.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "8364e31d0efc064f6d401a65c6f25079351c712a09309deb02a888c339cbb867", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "426d76395b0727a677a7455d329f80edff1a1b50f535851bab11d7c69d00c44b", "generation_seconds_batch": 22.614740025950596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7488818168640137, "target_z": 1.578125042157354, "ce": 5.355429172515869, "genuineness": 4.262581825256348, "identity": 0.3641171455383301, "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/emo_Distress/8364e31d0efc064f6d401a65c6f25079351c712a09309deb02a888c339cbb867.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "836c0f8d4c5cbb1ead3b9543e15a82e890d94169c872be98862b1579c5ef90ae", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6810d8f9cdefd46663553371081a31da5586fe1b5bd7a8ab65236849de13ea8d", "generation_seconds_batch": 21.12814907496795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1588057577610016, "target_z": -0.3671875085454096, "ce": 6.300607204437256, "genuineness": 4.796044826507568, "identity": 0.6635497808456421, "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/emo_Distress/836c0f8d4c5cbb1ead3b9543e15a82e890d94169c872be98862b1579c5ef90ae.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "838695d8f51568af2a90d871a5ffa49c2a9f57f8a5e7beeb3f326ab06e53528f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e638a2d3b279ab0cd249e25b54ba69ba116eadfd0a06b5806342269e673888ff", "generation_seconds_batch": 19.028010499081574, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10612252354621887, "target_z": -0.4316406245727295, "ce": 6.308549880981445, "genuineness": 4.344170093536377, "identity": 0.6514588594436646, "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/emo_Distress/838695d8f51568af2a90d871a5ffa49c2a9f57f8a5e7beeb3f326ab06e53528f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "83d96b716ca815bbebf61cee8cce0145c8acc42711f10f6ca7df536c55e1dab2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b2e8428d1e1b68f1c95fa03307b06791fd91bbaa6cc3ce874047de5af551a3e1", "generation_seconds_batch": 24.51323902606964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8468807935714722, "target_z": 0.4746093321305286, "ce": 6.006728172302246, "genuineness": 4.168440818786621, "identity": 0.6951981782913208, "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/emo_Distress/83d96b716ca815bbebf61cee8cce0145c8acc42711f10f6ca7df536c55e1dab2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "83e889efec69e54a35df7614b71f2a7e5ff5f212929a91844bd1b12e2fde99c2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "d87468ba66de25a4df544dd700439fb3bf74a53857a8a6b71463f7356c5191a6", "generation_seconds_batch": 22.225379720097408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.637393951416016, "genuineness": 3.9425034523010254, "identity": 0.3031167984008789, "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/emo_Distress/83e889efec69e54a35df7614b71f2a7e5ff5f212929a91844bd1b12e2fde99c2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "84fed3ed84c4ef477c8d7a8908f85eb4737ff3a7278672d37b06eaee7764143f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "4f6975be455af0b447ab81e1f78173fa8137a401ea9dfc33aa763bfa91e38535", "generation_seconds_batch": 22.242864853003994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3248378038406372, "target_z": -0.16406249373336632, "ce": 6.133810997009277, "genuineness": 3.9676074981689453, "identity": 0.707181990146637, "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/emo_Distress/84fed3ed84c4ef477c8d7a8908f85eb4737ff3a7278672d37b06eaee7764143f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "8546dd64a58c5d40409a26aec5fd53b0d111f9b37b49c8db2e9bcff878bcc1d1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "78a4944aff8e4988d6a9bffbac9379acad8744417344590a1204d48a92c12f44", "generation_seconds_batch": 16.022109235986136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9839282035827637, "target_z": 4.3124997675648595, "ce": 5.792276382446289, "genuineness": 4.036643981933594, "identity": 0.5368301868438721, "hypothesis": "J'ai détruit la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "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/emo_Distress/8546dd64a58c5d40409a26aec5fd53b0d111f9b37b49c8db2e9bcff878bcc1d1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "85e2ab05043c81deb114926b38f1a11cf71d879687c1ba4955b07123dd48178b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "01ce887759dde3a4a3b688bb34d86724fcf5b86a4e9da3a34443626de27e5a97", "generation_seconds_batch": 14.948860263917595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3982750475406647, "target_z": -0.07421874629698919, "ce": 6.340320587158203, "genuineness": 4.68307638168335, "identity": 0.3128323554992676, "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/emo_Distress/85e2ab05043c81deb114926b38f1a11cf71d879687c1ba4955b07123dd48178b.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": "86829023d6864f747613c430d810a8a12b80e04ceba2f317e60232cefc909b03", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f54f23550b44b5f6a247b8a7faad8901b92759f249a49ab7981378314695e63", "generation_seconds_batch": 20.207932176999748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.137188911437988, "target_z": 4.5000002187624855, "ce": 5.542081832885742, "genuineness": 3.478076457977295, "identity": 0.6439656019210815, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón. Y luego junto a la ventana. Llévatelas cuando te vayas, cuando te vayas, cuando te vayas, cuando te ventame tanto.", "wer": 0.5217391304347826, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/86829023d6864f747613c430d810a8a12b80e04ceba2f317e60232cefc909b03.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "86fb73d4562c1b10ef2b57b2f91ad3424dad7eb940fea4d50aa0e070e1e76f7e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "fd20056acfca7cd09fbd8b3c9987d1dff12e3a44fa95ea88fdd29e0ed60632a0", "generation_seconds_batch": 22.717480925959535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8255119323730469, "target_z": 1.671874976072853, "ce": 5.748591423034668, "genuineness": 4.111956596374512, "identity": 0.7232363820075989, "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/emo_Distress/86fb73d4562c1b10ef2b57b2f91ad3424dad7eb940fea4d50aa0e070e1e76f7e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "879bda949ec5b9445043cbf9dcdf0d28f3e5e451a863f8471a2a817c9672433a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "70d809eab77d2bfdaa173448f3fe9ca4055780389e9c30601212c85a6077f2b3", "generation_seconds_batch": 16.042383963940665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21627838909626007, "target_z": -0.2968750034181638, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.5112571716308594, "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/emo_Distress/879bda949ec5b9445043cbf9dcdf0d28f3e5e451a863f8471a2a817c9672433a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "87b655220d761bd9a24dbf457f4cfa0679b7c903f226e84218672775b004a818", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6b43316a004de586092738bf03f8ce4713a8601c23d1379e09b274ae639782e1", "generation_seconds_batch": 21.35383791301865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.208662748336792, "target_z": 2.140624937333663, "ce": 5.270045757293701, "genuineness": 3.9550557136535645, "identity": 0.41066741943359375, "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/emo_Distress/87b655220d761bd9a24dbf457f4cfa0679b7c903f226e84218672775b004a818.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "87c5093299a6b08873cc2f52a2d84dcafee1cc4a3db4641018133624e260182c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7884ed3b9d122f16195ff00b3a1994a72fa9d91c517f3ce38cb975bfb67c98bc", "generation_seconds_batch": 22.03762281697709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276854991912842, "target_z": 1.7968749851879566, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.3917166590690613, "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/emo_Distress/87c5093299a6b08873cc2f52a2d84dcafee1cc4a3db4641018133624e260182c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "87cc0eba206ad9078bc22a5ed8dc7116a6fff871f51532beecc18ddc79a3ab2b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9f2587cb1b0ecbb483645b713d89e1d1242d7b8940aca0aa265a668855fe73b1", "generation_seconds_batch": 16.325589043088257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7941975593566895, "target_z": 0.4101562161032086, "ce": 5.998785495758057, "genuineness": 4.394378662109375, "identity": 0.5543851852416992, "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/emo_Distress/87cc0eba206ad9078bc22a5ed8dc7116a6fff871f51532beecc18ddc79a3ab2b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "883e2cb134ea2f91697df7fbc4cea6f8eb2158d573a9ebadc43e68104041338e", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d569c0de0d4c06becad06e97cf6347835d1d51134eb348261278a0400f64d07b", "generation_seconds_batch": 15.100431557977572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2035067081451416, "target_z": -0.31249998632734466, "ce": 5.967014789581299, "genuineness": 4.369274139404297, "identity": 0.6377465128898621, "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/emo_Distress/883e2cb134ea2f91697df7fbc4cea6f8eb2158d573a9ebadc43e68104041338e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "8887a06eb5311a10fa7d37060192fb29595be5f18414b9d9fee562b121237805", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2dfa65dccdd04cae5fe4e7fa6705cd5cd10a034647cd6e552e7c77a7eacb7a42", "generation_seconds_batch": 21.801215845975094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.391274333000183, "target_z": 1.1406250102544915, "ce": 5.974957466125488, "genuineness": 4.268857479095459, "identity": 0.6573836803436279, "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/emo_Distress/8887a06eb5311a10fa7d37060192fb29595be5f18414b9d9fee562b121237805.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "888ef4d1175d4c5e7a344bcd9e471294a1d07ce85aab3affddf88a8e47918594", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4ea0a498eda5b0639d3507babfef7116c28ee73fd48c2c62d07fc6df275e9b79", "generation_seconds_batch": 22.456991170998663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4806761741638184, "target_z": 1.2499999817697929, "ce": 6.038498878479004, "genuineness": 4.306513786315918, "identity": 0.5375316143035889, "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/emo_Distress/888ef4d1175d4c5e7a344bcd9e471294a1d07ce85aab3affddf88a8e47918594.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "889c19fb799f5cefd969c54c27afcc59c4f905417b459510a9d7fd0a187ba2b2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1f0e6e4880736be9f69161e8278010c1544f6e15acc7b2a65b19d027c52e1483", "generation_seconds_batch": 23.130475674988702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3198001384735107, "target_z": 3.499999854158343, "ce": 5.442798614501953, "genuineness": 4.042920112609863, "identity": 0.4517107307910919, "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/emo_Distress/889c19fb799f5cefd969c54c27afcc59c4f905417b459510a9d7fd0a187ba2b2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "892809940c23512d3afc9310e388515b3edc1e449eac537af83c627a7007b7fa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b5ce6ee44eb14a3f04119e35629817b0503fe6f059b1e1ab0e45f3386d4fd2f8", "generation_seconds_batch": 24.96360229398124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6361478567123413, "target_z": 0.21679686802124884, "ce": 5.911416053771973, "genuineness": 4.444586753845215, "identity": 0.4557345509529114, "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/emo_Distress/892809940c23512d3afc9310e388515b3edc1e449eac537af83c627a7007b7fa.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "894fa1e3a04aaedf086953d50a7a170ddf8f8a3fd14cc59acc36ae6da010cd51", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e7916e027a189a5936ea14a6a8ba5570941259acb59085b77295d6c32aa1621d", "generation_seconds_batch": 22.71864444797393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5189913511276245, "target_z": 1.2968750945691994, "ce": 5.9431867599487305, "genuineness": 4.080576419830322, "identity": 0.5731848478317261, "hypothesis": "La porte est un tank. Encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "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/emo_Distress/894fa1e3a04aaedf086953d50a7a170ddf8f8a3fd14cc59acc36ae6da010cd51.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": "8a49304e5c6e7cb7db6d252cd5d0ca329a6aab3f99c6669cf97ee4c4f168127b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da621eaea2cfc9972bf73b01bfc14391acad932c42d5db4f04fe0ddb371badb7", "generation_seconds_batch": 14.85123584989924, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.895530700683594, "genuineness": 4.055472373962402, "identity": 0.6314345598220825, "hypothesis": "La carretera. Hay que ir a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "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/emo_Distress/8a49304e5c6e7cb7db6d252cd5d0ca329a6aab3f99c6669cf97ee4c4f168127b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "8a7c818e4c385ef1ba8c644cc691e06e0b0ab81ea4d25e4a14dcdec5e0863eb1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8371f8ca7a64211cc7678a5b1acd52b03b1478f48fbb7e7cd0205d5abf9594a7", "generation_seconds_batch": 20.553879959974438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.839932441711426, "genuineness": 3.314899444580078, "identity": 0.5434278249740601, "hypothesis": "The door is still open. He put your coat on the chair. Tell me when you are ready.", "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/emo_Distress/8a7c818e4c385ef1ba8c644cc691e06e0b0ab81ea4d25e4a14dcdec5e0863eb1.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": "8a7f32a79c388aa966eb70bbf1c95a0f4ba02aa77eff80e929eb6b736a66a92c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09523b2358304ecda3a1c459f437de2a3fba9944c0d1364982ba610a31bc7c61", "generation_seconds_batch": 21.84855532599613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.038822889328003, "target_z": 3.156249902012637, "ce": 4.952338695526123, "genuineness": 3.4623863697052, "identity": 0.33401843905448914, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Zoedan het kleine autek. Ik... ik wacht aan de andere kant.", "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/emo_Distress/8a7f32a79c388aa966eb70bbf1c95a0f4ba02aa77eff80e929eb6b736a66a92c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "8b210fd96faa400973d905582ef4ea8954052d4b0160b661d669f197c470fb98", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3ba244a86aa60a50059a3fdb73023e0ea5b3611129b4f27886101cb4addd695f", "generation_seconds_batch": 20.505957223009318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.566270112991333, "target_z": 2.5781248233948686, "ce": 5.895530700683594, "genuineness": 3.9299514293670654, "identity": 0.6572009325027466, "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/emo_Distress/8b210fd96faa400973d905582ef4ea8954052d4b0160b661d669f197c470fb98.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": "8b2680fc294948ca2246ab732149b0acbc896e8a3115ba4ccdd477f06d169cf0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2b62875db72af0ed86d39c8523c7610711270c7bd219809576da5856e8b08d25", "generation_seconds_batch": 16.458548591006547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3874664306640625, "target_z": 2.359374880364266, "ce": 6.006728172302246, "genuineness": 3.653805732727051, "identity": 0.6043711304664612, "hypothesis": "Someone moved the little blue chair. Yuce, stand here beside the tall bookshelf. We can put it back after lunch.", "wer": 0.13636363636363635, "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/emo_Distress/8b2680fc294948ca2246ab732149b0acbc896e8a3115ba4ccdd477f06d169cf0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "8c5573e833c03496d6be7e2a566fe40b11080f69298b52694715ecab11fb15f2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "27c8913068ac2e296efed44d24ae978027b4030e02815269faf9b4f84c82d1a8", "generation_seconds_batch": 21.973066508071497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.702950954437256, "target_z": 3.968749815419153, "ce": 6.038498878479004, "genuineness": 3.587907314300537, "identity": 0.6094750165939331, "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": 0.03999999999999915, "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/emo_Distress/8c5573e833c03496d6be7e2a566fe40b11080f69298b52694715ecab11fb15f2.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": "8ce0d45a5cbf18cc5154b974458d41510c7726b2ac826fb1286333a2db03dd83", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d38504093ca4064509969f93549cb0c62e507b613ab39767d97a5bdd0e1382ce", "generation_seconds_batch": 20.440868919948116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.447517156600952, "target_z": 3.656249938473051, "ce": 5.43088436126709, "genuineness": 4.093128204345703, "identity": 0.5374888777732849, "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": 0.03999999999999915, "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/emo_Distress/8ce0d45a5cbf18cc5154b974458d41510c7726b2ac826fb1286333a2db03dd83.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "8d034941a5e9840277b6f12cc5dab8ffe1b1d0abdf18670c3e0facb473195ab8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "df9c0ac0bc2ca4645ebdfba50827405cc5691efc09d8e44d418e25876887ef3f", "generation_seconds_batch": 22.006442469079047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3336183428764343, "target_z": -0.15332030772881297, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.7157491445541382, "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/emo_Distress/8d034941a5e9840277b6f12cc5dab8ffe1b1d0abdf18670c3e0facb473195ab8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "8d1298b1f8cd3410ee4f47ef800a1ed769bd4b15a065d83be8ab0719249dbf61", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5712613243cc74b3dad114d9354376ddbdbf4cbf2fcf982c27a01e8f23ab4007", "generation_seconds_batch": 19.87568703503348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9921588897705078, "target_z": 0.6523437884543432, "ce": 5.967014789581299, "genuineness": 3.8295347690582275, "identity": 0.4531702399253845, "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/emo_Distress/8d1298b1f8cd3410ee4f47ef800a1ed769bd4b15a065d83be8ab0719249dbf61.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "8d729cc56eac8e780dd16e056d70c5911485fc91f1a68be4cda67d12d1baf033", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "95a8698e757a8d72f731c0760321c82a3d575d421bcc912177fb96ef6a997bb7", "generation_seconds_batch": 17.221211244002916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8306679725646973, "target_z": 4.124999899733861, "ce": 5.847874641418457, "genuineness": 3.7918784618377686, "identity": 0.6728367805480957, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo. Dime cuándo estás listo.", "wer": 0.26666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/8d729cc56eac8e780dd16e056d70c5911485fc91f1a68be4cda67d12d1baf033.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "8e29bc2f190b07548b929017104cc3da9f519e72279a408e80ad5ba473ddaa55", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5c102fabe854e1613918fb018f21ae9657ef9314aae69e3f26e3c47ddb7431f5", "generation_seconds_batch": 16.042383963940665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1955243945121765, "target_z": -0.3222656165970139, "ce": 6.356205940246582, "genuineness": 4.494794845581055, "identity": 0.389851450920105, "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/emo_Distress/8e29bc2f190b07548b929017104cc3da9f519e72279a408e80ad5ba473ddaa55.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "8ecc28ca64af80ab3920695ff41c68541b31cfdad6664b8b25463b618010df04", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d467cd8deeb957e2ad45ccbb5f25b9f8440406442bbf743ccb7bd46eb25138b3", "generation_seconds_batch": 23.171015249099582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2725212574005127, "target_z": 2.218749979491017, "ce": 5.855817794799805, "genuineness": 3.8922953605651855, "identity": 0.3986768126487732, "hypothesis": "De deur staat nog open. Ik. Ik. 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/emo_Distress/8ecc28ca64af80ab3920695ff41c68541b31cfdad6664b8b25463b618010df04.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "8f7587fa72da223a03b81d4de6d2a004e45f7385393544a239c50abbe947b701", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8413b65003bc8d35cfba9433d5415a5dc2e14158ddc01cf7b50deeb8cbfd58ca", "generation_seconds_batch": 21.446575654903427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5355707406997681, "target_z": 0.09374997037591343, "ce": 5.990842819213867, "genuineness": 4.3504462242126465, "identity": 0.4468029737472534, "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/emo_Distress/8f7587fa72da223a03b81d4de6d2a004e45f7385393544a239c50abbe947b701.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "8fca474ec06c5c9454a376bcba09ba3846e13366d08bb0bd126e570638c24190", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6d37f537be18f99292fc1a53104b22f7ec82e0fe1c54a4fd56417f15181110f1", "generation_seconds_batch": 15.89495463098865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6939871311187744, "target_z": 2.7343749077095763, "ce": 6.3641486167907715, "genuineness": 4.068024158477783, "identity": 0.39634087681770325, "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": 0.03999999999999915, "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/emo_Distress/8fca474ec06c5c9454a376bcba09ba3846e13366d08bb0bd126e570638c24190.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "8ffcbd64bacdd8c3897ccfceca6dfe267d9883833fc942bec09b295b1ed5ad14", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "936db3672e9a50fe75ea67d531ad97b39035f813cd2a88f363aebba417aa8326", "generation_seconds_batch": 22.596272445051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11729776859283447, "target_z": -0.4179687349031097, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.5476564168930054, "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/emo_Distress/8ffcbd64bacdd8c3897ccfceca6dfe267d9883833fc942bec09b295b1ed5ad14.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "90a1925ec66b856b058f2071ba7e06bc9a0da68f187b35513b29d322c35dd092", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "631f4f6fbc229ec4c4622110edeaf3d31050d0ab2c16d6cf6f23606ecf47cbce", "generation_seconds_batch": 15.454478994011879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6856381893157959, "target_z": 0.27734376110903247, "ce": 6.157639026641846, "genuineness": 4.607763767242432, "identity": 0.6451076865196228, "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/emo_Distress/90a1925ec66b856b058f2071ba7e06bc9a0da68f187b35513b29d322c35dd092.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "9104aaa517785861db682b03748016b7e46e285d4a0a51775f5726ece034b459", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0e8d77fb596e9e5c04438385de43e00a71a3621ef0c056385c85cf5cb13111f8", "generation_seconds_batch": 21.69943397201132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33920595049858093, "target_z": -0.1464843811242102, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.7004990577697754, "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/emo_Distress/9104aaa517785861db682b03748016b7e46e285d4a0a51775f5726ece034b459.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": "927294720001e64fe478a0f81a4b7923d1e16aa0f5af25f2efb45a5cbe11e98e", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46567649956d1d6cffffaedc6918df5cba7503197eb7838310a495d14860af87", "generation_seconds_batch": 14.941692473948933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.754037857055664, "target_z": 4.031249965818362, "ce": 5.6413655281066895, "genuineness": 3.735394239425659, "identity": 0.5766751766204834, "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/emo_Distress/927294720001e64fe478a0f81a4b7923d1e16aa0f5af25f2efb45a5cbe11e98e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "927baced4e2bd64b4ebac794916ceec29eb315c17e4efa3a75a52261468000c8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "2e0df66b989c73c222068d0f9205378a8c6051f25ad0e74d8536cde33ebb3e32", "generation_seconds_batch": 23.082730310969055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4768683910369873, "target_z": 2.468749997721224, "ce": 5.71682071685791, "genuineness": 4.406930446624756, "identity": 0.5021891593933105, "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/emo_Distress/927baced4e2bd64b4ebac794916ceec29eb315c17e4efa3a75a52261468000c8.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": "940bd313d27ae85af3d5f4d9fc076c368f2e9774ba017bfec62dc039dac99e00", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0441150441eb35074f24bf3f3700ad9aa57b0937bf342a123daf02db05f92b8", "generation_seconds_batch": 17.347064743051305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6984098553657532, "target_z": 0.29296872578800615, "ce": 5.49045467376709, "genuineness": 4.394378662109375, "identity": 0.6247259974479675, "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/emo_Distress/940bd313d27ae85af3d5f4d9fc076c368f2e9774ba017bfec62dc039dac99e00.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": "940e916cb9fc1445c8430d9ab3fbd38eff2dc6ab8bffbdc85781adc87cc8901a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7025a1a4cc92ed0f6a459f7ee5b9d0a51582f66630f3a149f0996344a8f719d1", "generation_seconds_batch": 16.261885207961313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.793582797050476, "target_z": 1.632812600835833, "ce": 5.847874641418457, "genuineness": 3.9425034523010254, "identity": 0.5616402626037598, "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/emo_Distress/940e916cb9fc1445c8430d9ab3fbd38eff2dc6ab8bffbdc85781adc87cc8901a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "954a30eaebd489b7baff52b484ba3bf23e34890d8199ba4a9a039fcfd4192e10", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5fffce5a72e137687c6cadc147b54d1345448239bcbf684e09f1af59bb33691d", "generation_seconds_batch": 15.454478994011879, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2380139827728271, "target_z": 0.9531249965818361, "ce": 6.062326908111572, "genuineness": 4.356721878051758, "identity": 0.7142744064331055, "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/emo_Distress/954a30eaebd489b7baff52b484ba3bf23e34890d8199ba4a9a039fcfd4192e10.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "9560a0451b76b683bc02ab4863952db7e4dd2672d78b2fcd513ef90d7e048cdf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dc383f8608aac90e5646725206cc8fdf6a99c24a2a6a3c6f98b19f76e22c666d", "generation_seconds_batch": 22.596272445051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5283867120742798, "target_z": 0.08496096876195673, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.6625557541847229, "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/emo_Distress/9560a0451b76b683bc02ab4863952db7e4dd2672d78b2fcd513ef90d7e048cdf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "95a05a41495915cd77b9c6932b757926489cc5b9060d5749785cb22f641eb03b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a30fe1bd2204ff4d29c1cc269ac5f87a29390ebcc3c130e5c3551aa69ab24e02", "generation_seconds_batch": 20.961575507069938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6301286220550537, "target_z": 2.6562498655522226, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.5913540124893188, "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/emo_Distress/95a05a41495915cd77b9c6932b757926489cc5b9060d5749785cb22f641eb03b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "95f13f9a46fcd82703365e62cba387127cf225fdca1e9642da0b25ae2dd9aa97", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c6419dfe10e90cc64925103934a2cfecfbe173eb4d3b1885f85c506d0b43c4f2", "generation_seconds_batch": 22.0371443569893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276854991912842, "target_z": 1.7968749851879566, "ce": 5.927301406860352, "genuineness": 4.18099308013916, "identity": 0.5152667760848999, "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/emo_Distress/95f13f9a46fcd82703365e62cba387127cf225fdca1e9642da0b25ae2dd9aa97.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "962c02941ed8ad6479228761f35bc94e9101bd13c0e90519274d85db1b247b07", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7a5ffc6e770a9068d20541a93e1464da7f9e2d55a978ab40f5e60fd768237056", "generation_seconds_batch": 20.445009405026212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0490164756774902, "target_z": 1.945312331940278, "ce": 5.6413655281066895, "genuineness": 4.582659721374512, "identity": 0.6117045879364014, "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/emo_Distress/962c02941ed8ad6479228761f35bc94e9101bd13c0e90519274d85db1b247b07.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": "96c8c1d4ba1734e8c7489e6a8e2f7d32c9399483fa5176cd2205b9a919151dac", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d217a6e794c3f43d237812fdf360f18d419235a883d30271ad7bba4586c75941", "generation_seconds_batch": 20.64027615392115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.923877716064453, "target_z": 3.015625001139388, "ce": 6.078212261199951, "genuineness": 3.898571252822876, "identity": 0.6333808898925781, "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/emo_Distress/96c8c1d4ba1734e8c7489e6a8e2f7d32c9399483fa5176cd2205b9a919151dac.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "97050ab1700101b19c08084fdbca88fff2645b34cbf50e3923ee8726042c24d8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1205392ff2b845a0049d0a8fac5a149e5942bc74f1c194145716f858cb26228f", "generation_seconds_batch": 20.445009405026212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4046608805656433, "target_z": -0.06640626395750232, "ce": 6.348263263702393, "genuineness": 4.419482707977295, "identity": 0.4672873020172119, "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/emo_Distress/97050ab1700101b19c08084fdbca88fff2645b34cbf50e3923ee8726042c24d8.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": "97d5e4b0abfd7bf669480dfb2fd7717d0dc5b9ca8f6f195e1ecf2728d3f59076", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acbe8cec3005a8d5a38d332f314b21e8d3778a88e43016d95954385beb6be699", "generation_seconds_batch": 22.77610422403086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9111058712005615, "target_z": 2.999999817697929, "ce": 6.006728172302246, "genuineness": 3.7918784618377686, "identity": 0.47525084018707275, "hypothesis": "Wrote the number on the envelope. Read it carefully. Jack, the last two digits. Call me when you have a moment.", "wer": 0.13043478260869565, "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/emo_Distress/97d5e4b0abfd7bf669480dfb2fd7717d0dc5b9ca8f6f195e1ecf2728d3f59076.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "97ddfd25811f6bb6b02a12b6fdae9795e089dba8519dabd2660d88b6a206f6d6", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6b782616908f15c8d6668026060208297c83a7b6505f8eb86eaf8a11a7b7a0fb", "generation_seconds_batch": 21.71621317602694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8306679725646973, "target_z": 4.124999899733861, "ce": 5.8875885009765625, "genuineness": 3.9676074981689453, "identity": 0.4967424273490906, "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/emo_Distress/97ddfd25811f6bb6b02a12b6fdae9795e089dba8519dabd2660d88b6a206f6d6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "983ee0eea9fc91f1cbfac24797b36406ad7774014c699bced0654070f6565c1a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0a73e3e73c489cdc6fac57c8067a6f9a312d64070c4d9e62d0cb0bf18bbce6b0", "generation_seconds_batch": 23.43277668498922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 5.732706069946289, "genuineness": 4.042920112609863, "identity": 0.635512113571167, "hypothesis": "J'ai essayé de trouver la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "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/emo_Distress/983ee0eea9fc91f1cbfac24797b36406ad7774014c699bced0654070f6565c1a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "98c2bc10c5e4ce81ea6f9f0dea0ab03edcf0857388d8ec00b685959a969cf96b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d25a1f461eda8b8ff7069eb15b1393d676c54ef96cf4231902057d409ab3e63a", "generation_seconds_batch": 21.48531643592287, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6417354941368103, "target_z": 0.22363283108626586, "ce": 6.062326908111572, "genuineness": 4.6956281661987305, "identity": 0.6381857991218567, "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/emo_Distress/98c2bc10c5e4ce81ea6f9f0dea0ab03edcf0857388d8ec00b685959a969cf96b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "990422ee2d240dc0b67cd74e3f1b2d5b33ec660c52f69af417004b7676304899", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "314acd791eedf761dd2e9adb52558f3aa690573dd8da9f6888a0ca95e5433644", "generation_seconds_batch": 16.416928112041205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.323607921600342, "target_z": 2.2812498382069117, "ce": 5.879645347595215, "genuineness": 4.13078498840332, "identity": 0.6674270629882812, "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/manual-comparison-v1/audio/emo_Distress/990422ee2d240dc0b67cd74e3f1b2d5b33ec660c52f69af417004b7676304899.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "99b3c801638335f22227ae5b79b7860cecc0f483b3a333009e26bd857934c94f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "14b65a7cc7d417283ecaff7e257160ec5d69b7b92b1ec361eaa5cc40861e9873", "generation_seconds_batch": 22.112720465986058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20829609036445618, "target_z": -0.30664061545762594, "ce": 6.229123115539551, "genuineness": 4.293961524963379, "identity": 0.2912404537200928, "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/emo_Distress/99b3c801638335f22227ae5b79b7860cecc0f483b3a333009e26bd857934c94f.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "70b3a2293d760f2ec3c6bc458b90a879c2ce5dda844a9ba92d78d38fb20efe12", "generation_seconds_batch": 16.88169759698212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25459349155426025, "target_z": -0.24999998176979288, "ce": 6.38797664642334, "genuineness": 4.557555198669434, "identity": 0.5391663312911987, "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/emo_Distress/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "99dad0f7152179bb7c3be482aab0d868cb90a2a59579fb217123a1bdb29651d1", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8e2f46cec06a9eca104ad13bf6f36047330c74a578274b6de5da41e73fa5fb2", "generation_seconds_batch": 18.449761335970834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2725212574005127, "target_z": 2.218749979491017, "ce": 5.927301406860352, "genuineness": 4.080576419830322, "identity": 0.48845723271369934, "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/emo_Distress/99dad0f7152179bb7c3be482aab0d868cb90a2a59579fb217123a1bdb29651d1.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": "9a45f6721aecc454f9c61743d0f43056cd1c03aa81c2759d8d94485f447a161c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2972a8939d7aa831c4d774758ea857553b24af4fd4cbb4f00ab0a21f551ca0c5", "generation_seconds_batch": 21.978102955035865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.421973705291748, "target_z": 3.624999863273447, "ce": 5.700935363769531, "genuineness": 3.8797430992126465, "identity": 0.4340197443962097, "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/emo_Distress/9a45f6721aecc454f9c61743d0f43056cd1c03aa81c2759d8d94485f447a161c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "9b6a7f55ac68645748da31c2ea9b41cd068595532d73b36af5c6097a1aab6068", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "474cfc7006bc02e81c096b73138103d45e3696bb48669f7dcccaab6c19d33d74", "generation_seconds_batch": 22.06757870898582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0298590660095215, "target_z": 1.9218749943030602, "ce": 5.522225379943848, "genuineness": 3.3588318824768066, "identity": 0.3937276303768158, "hypothesis": "I found the little fox. It was beside the whole window. We can look inside together.", "wer": 0.125, "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/emo_Distress/9b6a7f55ac68645748da31c2ea9b41cd068595532d73b36af5c6097a1aab6068.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "52463b742a54bd98f920817e9ba206ad48f2c2ce24e9a7da869b8f2286237cad", "generation_seconds_batch": 13.576297940104268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08217558264732361, "target_z": -0.4609375153817373, "ce": 6.24500846862793, "genuineness": 4.287685871124268, "identity": 0.7122232913970947, "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/emo_Distress/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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": "9c3c6d71e2fb518b17aa13186d49e7eb3626a58301d6bf84ea0a41654cb7e883", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "47ce40b8e6c4b3bd3e742f9d74ff115c9054d6790f6c00b2ddd0dbb2577f449f", "generation_seconds_batch": 21.84855532599613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3581151962280273, "target_z": 3.5468748211160928, "ce": 5.661221981048584, "genuineness": 3.380797863006592, "identity": 0.27151021361351013, "hypothesis": "De weg gaat linksaf. Naar de brug. Loop verder. Tot aan het kleine houten. Ik wacht aan de andere kant.", "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/emo_Distress/9c3c6d71e2fb518b17aa13186d49e7eb3626a58301d6bf84ea0a41654cb7e883.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "9c758acfff8c7505dc54593f94712793e6b23300079f6b55efcbbbb677970922", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "eaffce226b69ed23dff69aa81764c89a1f44ed353bfde493fd79485eb07e0529", "generation_seconds_batch": 16.74752983392682, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1581908464431763, "target_z": 0.8554686938851437, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.5045904517173767, "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": 0.03999999999999915, "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/emo_Distress/9c758acfff8c7505dc54593f94712793e6b23300079f6b55efcbbbb677970922.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "9c9325abdbe622182c72399e43f3cdd3d141563b3d430e5bdb7503f05150677d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c055e66394659cc97b11eecdbfeff36a948300435cfe7239ea78b9b8aa4c6efe", "generation_seconds_batch": 21.857947867945768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.115453004837036, "target_z": 3.249999835928136, "ce": 5.700935363769531, "genuineness": 3.722842216491699, "identity": 0.5183460712432861, "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": 0.03999999999999915, "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/emo_Distress/9c9325abdbe622182c72399e43f3cdd3d141563b3d430e5bdb7503f05150677d.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "efaac3c639891cf0d25d206375cd2e1929e41ffb8f2b23c1f7589133777fb0f3", "generation_seconds_batch": 17.135520527954213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23543593287467957, "target_z": -0.27343750170908193, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.553913950920105, "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/emo_Distress/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "9cbb28e1d562c57c1833c85c1c396557b4b17e96adfbca957e2c1bb8108c0558", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ed416415f1c6e1d08991d5305ded267fbc74515b9a24e2335c942ac17e3b3d2d", "generation_seconds_batch": 14.432247332064435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.132032632827759, "target_z": 2.046875003418164, "ce": 6.046441555023193, "genuineness": 4.093128204345703, "identity": 0.5317604541778564, "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/emo_Distress/9cbb28e1d562c57c1833c85c1c396557b4b17e96adfbca957e2c1bb8108c0558.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": "9cfacc86f53fa73d5f3d5aac84cfee1dd65d386b335d9edf4066a507b4d16ccd", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afd1a2c76538a6c94411d4b1720f92f1f7845a1f9e7c8f0931655399dfdbbf64", "generation_seconds_batch": 21.869606247986667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6007773876190186, "target_z": 3.843749806304049, "ce": 5.689021587371826, "genuineness": 3.923675537109375, "identity": 0.5728915929794312, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, 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/emo_Distress/9cfacc86f53fa73d5f3d5aac84cfee1dd65d386b335d9edf4066a507b4d16ccd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "9d9f8e42916268e43b04183bca8dac2aa434a6c14aab597bc0fbf452d217a379", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "51cbfd7ed86ed8f06dc7b1843bc222a9018dad30e3a026a661d52928ec911bb3", "generation_seconds_batch": 22.73668335902039, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0592103004455566, "target_z": 0.7343750535512334, "ce": 5.903473377227783, "genuineness": 4.055472373962402, "identity": 0.2556828260421753, "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/emo_Distress/9d9f8e42916268e43b04183bca8dac2aa434a6c14aab597bc0fbf452d217a379.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "9dbe7ada996d7e8af0994b96118d174f57139f01c573522aee2e88f5133f76f0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5fa6c098a1d91b40fa44c3f719507f2daf4258a646dd3769dcd6ea8fa0793426", "generation_seconds_batch": 21.146292528952472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4844839870929718, "target_z": 0.03125000227877589, "ce": 5.935244083404541, "genuineness": 4.532451152801514, "identity": 0.602175235748291, "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/emo_Distress/9dbe7ada996d7e8af0994b96118d174f57139f01c573522aee2e88f5133f76f0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "9df4ee1ffc73e0e67d3157cb79175f60024331810abd94e877a9503a151cf511", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6e5e777ab413675915061dfca686e5b8b7e85f7fa30f120d408b251d5caa651d", "generation_seconds_batch": 20.76595830998849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.562462329864502, "target_z": 3.7968748393463, "ce": 5.5738525390625, "genuineness": 3.7040140628814697, "identity": 0.36275047063827515, "hypothesis": "De deur staat nog open. Ik heb je je was op de stoel gelegd. Zeg maar wanneer je klaar bent.", "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/emo_Distress/9df4ee1ffc73e0e67d3157cb79175f60024331810abd94e877a9503a151cf511.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "9e7cbaac1e2f559718518189a7e3051cee872fc5890cc7c3e30a48a69baf22fa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ee010ca791f50f4c7d0b212813c234103dd91b7111e5fd22aeec4c6507789589", "generation_seconds_batch": 20.146268317941576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.298064708709717, "target_z": 2.2500000546906214, "ce": 5.383228778839111, "genuineness": 3.8671910762786865, "identity": 0.5386902689933777, "hypothesis": "He encontrado la cajita. Estaba junto, pasó. Junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "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/emo_Distress/9e7cbaac1e2f559718518189a7e3051cee872fc5890cc7c3e30a48a69baf22fa.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": "9f27847ea3fb750fdd2afbac467cbefcfc6e9c04355819ed7ad00d74117a5843", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6371f53c075bd24b1a95c251b4c6b2d6a75aabcef213fcabd407ec11e7c6fcc0", "generation_seconds_batch": 17.16468862001784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1262617111206055, "target_z": 0.8164063186481236, "ce": 6.086154937744141, "genuineness": 4.218649387359619, "identity": 0.484902024269104, "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/emo_Distress/9f27847ea3fb750fdd2afbac467cbefcfc6e9c04355819ed7ad00d74117a5843.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "9f519cb20a8a4c66c2c5e7dad78aaff8bd173655843e504055c5c824e41ed0f2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0e14dbc8a85084b98810f845f0e1aa7c1f0265369802850cc0eee01875a564a5", "generation_seconds_batch": 21.1292721190257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9149138927459717, "target_z": 1.7812500934298114, "ce": 6.054384231567383, "genuineness": 3.8169827461242676, "identity": 0.7104790806770325, "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/emo_Distress/9f519cb20a8a4c66c2c5e7dad78aaff8bd173655843e504055c5c824e41ed0f2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "9fbdeeecd9ca22528dda3842dbe6c8abcd7924440695e3eb107684a3d66453bf", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0024d232df6e89a73a302bc4f9f8adaa95062ee5abb5c81bfea1b0c43d33ff4d", "generation_seconds_batch": 16.59805244009476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19871732592582703, "target_z": -0.3183593571970634, "ce": 6.054384231567383, "genuineness": 4.042920112609863, "identity": 0.4608747959136963, "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/emo_Distress/9fbdeeecd9ca22528dda3842dbe6c8abcd7924440695e3eb107684a3d66453bf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a02e63f344cab817bbafe728bcccbae3b85c65b3fa6d4730c55bf305712cc013", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "25fa7cd266b6b8ac50d2cf755273ef2c12379cd28b93ac0df82dadf7d23036f4", "generation_seconds_batch": 22.530892045935616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2827149629592896, "target_z": 1.0078125552603154, "ce": 5.736677646636963, "genuineness": 4.256305694580078, "identity": 0.42690178751945496, "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/emo_Distress/a02e63f344cab817bbafe728bcccbae3b85c65b3fa6d4730c55bf305712cc013.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "a07f6ec8a9b0b0ee7c81d7e9b3b47f00f0d5f24c65f6c2cc4d8d0b231903ab96", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bd3f3e070773bb4e8a710b1e990265df46b702934b5423667067304236114ac8", "generation_seconds_batch": 21.098321545054205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19392791390419006, "target_z": -0.3242187645271963, "ce": 6.1020402908325195, "genuineness": 4.595211505889893, "identity": 0.34711551666259766, "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/emo_Distress/a07f6ec8a9b0b0ee7c81d7e9b3b47f00f0d5f24c65f6c2cc4d8d0b231903ab96.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": "a0a4f81fc3bac07828d4ccae46d6803aa5210a82cc4cf95f302e8d5825910dd9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef71272b731f44d1be2f948be566e764ea3c508bcb3cbd90b987d59639e60549", "generation_seconds_batch": 17.264412602060474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.204854965209961, "target_z": 3.3593749532850943, "ce": 5.824047088623047, "genuineness": 3.8671910762786865, "identity": 0.5360931158065796, "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/emo_Distress/a0a4f81fc3bac07828d4ccae46d6803aa5210a82cc4cf95f302e8d5825910dd9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a0e817e1fc9044092f079bc00c16ce7348abae52431ab6a7c719078b95867ac2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "674d38fbe1e6463ef3cd7cbd38d631efe253e537238ffef1d4aa219da35835f9", "generation_seconds_batch": 14.72060722799506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17796331644058228, "target_z": -0.34374998860612055, "ce": 5.752562999725342, "genuineness": 4.18099308013916, "identity": 0.7530670762062073, "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/emo_Distress/a0e817e1fc9044092f079bc00c16ce7348abae52431ab6a7c719078b95867ac2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "a15a6a16aa06ce06c8b12ea2e9b50f20cf5a6db4019c403292b26e620bcdebd3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ce550b1d25c4baad6e8430fc0051b659b87da483845ce50051ce568f84ec504a", "generation_seconds_batch": 23.43277668498922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2687134742736816, "target_z": 3.4374999954424483, "ce": 5.720792293548584, "genuineness": 3.7291181087493896, "identity": 0.7237979173660278, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder ensemble ce qu'elle contient. Il faut moins que tu rassanges mes trucs.", "wer": 0.47368421052631576, "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/emo_Distress/a15a6a16aa06ce06c8b12ea2e9b50f20cf5a6db4019c403292b26e620bcdebd3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "a1ed6c3f43cc41dbd155b34201bf6ba14395d035cdf2624cafabef3c5793b53c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5fc2d6751d7f1ee08e3208414aaf2d08d06a378f18cce609ad09b62949deea1d", "generation_seconds_batch": 22.112720465986058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19073501229286194, "target_z": -0.32812498746673263, "ce": 6.2767791748046875, "genuineness": 4.2249250411987305, "identity": 0.15397579967975616, "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/emo_Distress/a1ed6c3f43cc41dbd155b34201bf6ba14395d035cdf2624cafabef3c5793b53c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "a1fd1360c4f197947fd2a74dc760bcb3718dccd2f6e62dfd423f8a6ac221a809", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "65ac9378625bad0c56c6790051ab87a23a460034dc9bfb08ba919d6fd96c7853", "generation_seconds_batch": 21.95400247001089, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5196061730384827, "target_z": 0.07421878275740341, "ce": 6.213237762451172, "genuineness": 4.65797233581543, "identity": 0.538948655128479, "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/emo_Distress/a1fd1360c4f197947fd2a74dc760bcb3718dccd2f6e62dfd423f8a6ac221a809.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "a227a64f6652ae33227bc38cbf5bd1a09c2c83c21975670ce37131767d58a360", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "2cb127f3d36fc6b947411ece68e4ab70554f2ccfe5bb80a2dabfa65c4f306129", "generation_seconds_batch": 15.889340206049383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.25594162940979, "target_z": 3.421874812000989, "ce": 5.80021858215332, "genuineness": 4.18099308013916, "identity": 0.251994252204895, "hypothesis": "La porte est encore ouverte. J'ai posé trop mon tout 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/emo_Distress/a227a64f6652ae33227bc38cbf5bd1a09c2c83c21975670ce37131767d58a360.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a2f80ab3454800417c5a5ff6376be1c055ccd755405a32c36ded2ae4d6d660cf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a43e4c5704bf33009df0704e3b644d05ed6acffa28b6b8f01ca662d56ffa06de", "generation_seconds_batch": 20.72976193507202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0515944957733154, "target_z": 3.171874793770782, "ce": 6.054384231567383, "genuineness": 4.1998209953308105, "identity": 0.5539660453796387, "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/emo_Distress/a2f80ab3454800417c5a5ff6376be1c055ccd755405a32c36ded2ae4d6d660cf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a2fb232861c336afcf692f59bdf809cad6181c12a4edf4b1a145a0eb4443eb40", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "754141006dc05481c8aab11cffa970db764e14faeccfffab7fb27f83aff65500", "generation_seconds_batch": 25.630187592003495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.821704149246216, "target_z": 2.8906249920242844, "ce": 5.657250881195068, "genuineness": 4.111956596374512, "identity": 0.539167046546936, "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/emo_Distress/a2fb232861c336afcf692f59bdf809cad6181c12a4edf4b1a145a0eb4443eb40.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": "a381ea16c633be508cd76c3e3020e9c9f810a8487da8c184fbd23462b53e35d3", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8c29eaf36f67ba2780a083769325ce17cac85e03e28562e4e18cd812bf98e815", "generation_seconds_batch": 16.447657427052036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6263208389282227, "target_z": 3.874999881503654, "ce": 5.669164657592773, "genuineness": 3.923675537109375, "identity": 0.6697537899017334, "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": 0.03999999999999915, "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/emo_Distress/a381ea16c633be508cd76c3e3020e9c9f810a8487da8c184fbd23462b53e35d3.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": "a3a46957191dc6b8823fb56a93db7c03f244c7ec132913bb86db83c9c1627778", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "747107a132129c1dd8fba3a6c71d9263f87cb5370643753d45f60e5323aa767c", "generation_seconds_batch": 20.207932176999748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.72849440574646, "target_z": 3.9999998906187573, "ce": 5.577824115753174, "genuineness": 3.575355052947998, "identity": 0.7161595821380615, "hypothesis": "Las llaves están en la mesa de la cocina. Mire, en el cajón. Y luego, junto a la ventana. Llévatelas cuando te vayas.", "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/emo_Distress/a3a46957191dc6b8823fb56a93db7c03f244c7ec132913bb86db83c9c1627778.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a437ae7690b77151987395822857047cca274e0cfba9a1f9824ee1aa68f324bb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "c6aac25110428054bce40f6a364789a122ae709a4849841cdd53be2f27535fbf", "generation_seconds_batch": 22.94620914303232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4730606079101562, "target_z": 3.6875000136726555, "ce": 5.808161735534668, "genuineness": 4.017816066741943, "identity": 0.4791674315929413, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo, ni.", "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/emo_Distress/a437ae7690b77151987395822857047cca274e0cfba9a1f9824ee1aa68f324bb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "a438b68b857c5fbd99d2f9c87e71840122a4aa4e87d8def1339deba5f9eb11ce", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "45e30dd43b377890575e9544619134fcebfde8506baa051704e4ac600673bc74", "generation_seconds_batch": 21.898009496042505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9276854991912842, "target_z": 1.7968749851879566, "ce": 5.236289024353027, "genuineness": 4.15588903427124, "identity": 0.716158390045166, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "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/emo_Distress/a438b68b857c5fbd99d2f9c87e71840122a4aa4e87d8def1339deba5f9eb11ce.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": "a4c801dd20d82e0003aa9dffa32536a6f48d3f19a5e21ffae2d15b7e8a906d63", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30755afc3f56252dd4979a0ffdb2030f729796586ceb47946389b1f4a305c4bf", "generation_seconds_batch": 15.62638532789424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.783389091491699, "target_z": 2.8437500250665346, "ce": 5.6334228515625, "genuineness": 3.7291181087493896, "identity": 0.3904423415660858, "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/emo_Distress/a4c801dd20d82e0003aa9dffa32536a6f48d3f19a5e21ffae2d15b7e8a906d63.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a4fe88cc31968c34cb41f55657051e9cc106b0874f522f6035d124f46ab339ec", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "eba915bc082bae369c6398230380783324a50efa894ca0ba550a71174a017a96", "generation_seconds_batch": 17.402943643042818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1007182598114014, "target_z": 0.7851562434485193, "ce": 5.879645347595215, "genuineness": 4.18099308013916, "identity": 0.4577327370643616, "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/emo_Distress/a4fe88cc31968c34cb41f55657051e9cc106b0874f522f6035d124f46ab339ec.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "a55708efb15dc37a6653976d9a36986ef984aca65f66395acb6443849a2bb44a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1ced488be24e0585fd665ab50492c2485c7193d21d525c390eedf6a1a48772c2", "generation_seconds_batch": 22.589266129070893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8957562446594238, "target_z": 1.7578124641092798, "ce": 5.839932441711426, "genuineness": 4.030367851257324, "identity": 0.5923380255699158, "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/emo_Distress/a55708efb15dc37a6653976d9a36986ef984aca65f66395acb6443849a2bb44a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "a5c514bada1da69d30bb987d5e119c3d0c5edb91907eb1fc79df75a160b5c001", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "97672233479f0246187e2c5abdb03294f0997cc1093e3d15c72251740f810272", "generation_seconds_batch": 21.292625873931684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37831926345825195, "target_z": -0.09863282197116229, "ce": 5.847874641418457, "genuineness": 4.419482707977295, "identity": 0.7022088766098022, "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/emo_Distress/a5c514bada1da69d30bb987d5e119c3d0c5edb91907eb1fc79df75a160b5c001.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "a61d1ef9851eda7db255a3e6e9ee6b5d602cec2fc6e97f39198109fe66078396", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f9241049b644e25f90692cab92ab66a1ae50011a527b3bffafbaa53d4303b2c4", "generation_seconds_batch": 17.208894992014393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9506508111953735, "target_z": 0.6015624527154003, "ce": 5.879645347595215, "genuineness": 4.381826400756836, "identity": 0.49531883001327515, "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/emo_Distress/a61d1ef9851eda7db255a3e6e9ee6b5d602cec2fc6e97f39198109fe66078396.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": "a61f1fa82e8d9b823afdbf0af33d53b0b9b6a489a417968e68740a61b068ff78", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "79c3f7daed6dea1a7fcb213acbc14b9a7e74a2e404aa4129683b43ffadbf5dd1", "generation_seconds_batch": 16.09638563496992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.9583849906921387, "target_z": 4.281249984048569, "ce": 5.669164657592773, "genuineness": 3.8420867919921875, "identity": 0.5064511299133301, "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/emo_Distress/a61f1fa82e8d9b823afdbf0af33d53b0b9b6a489a417968e68740a61b068ff78.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": "a6239ce704bd1a0dab131853677f19d98606d9f91d2163007ad5d40f5407c99c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "11927ce2fea3544c428e797d380993a17d651b84324aac47352afe8b78a71728", "generation_seconds_batch": 22.19628257700242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.25594162940979, "target_z": 3.421874812000989, "ce": 6.006728172302246, "genuineness": 3.9048471450805664, "identity": 0.513558030128479, "hypothesis": "The keys are on the kitchen table. I checked the drawer and looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "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/emo_Distress/a6239ce704bd1a0dab131853677f19d98606d9f91d2163007ad5d40f5407c99c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "a638d604c297680bb026da4e5ace6424aca26cf76544c05b9225b5dbff0027ee", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a1ebeb613fe9286b7594fe6594ba8752e638292986a7ee46a25850d3ca8f17a2", "generation_seconds_batch": 21.70558037504088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8277232646942139, "target_z": 0.4511718486516538, "ce": 5.919358730316162, "genuineness": 3.911123275756836, "identity": 0.6614476442337036, "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/emo_Distress/a638d604c297680bb026da4e5ace6424aca26cf76544c05b9225b5dbff0027ee.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "a67836cd31b1df8b88d8d2f7b6bc35abab9e6f8aea47764eb034e318496362fa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fd5c92cc21fd4389b3f0e92df6a8a4fa3590183b852da7e74e435de1265ce8b4", "generation_seconds_batch": 23.21059801708907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2539786100387573, "target_z": 0.9726562571211746, "ce": 6.0146708488464355, "genuineness": 4.369274139404297, "identity": 0.5733767151832581, "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/emo_Distress/a67836cd31b1df8b88d8d2f7b6bc35abab9e6f8aea47764eb034e318496362fa.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "a690bc747e1d50a2f686ea4cf2b1372966f6e04a313325515df05addb0cd54ad", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "eda4ae5061a473594fbc231467a2278c2497820660930305ddaa61e55f5d8f91", "generation_seconds_batch": 22.213588834973052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.5101044774055481, "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/emo_Distress/a690bc747e1d50a2f686ea4cf2b1372966f6e04a313325515df05addb0cd54ad.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "a770bee00d49b442b497dd652591188e096e5d11aac9e0eb42554adfe808eafb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d3f147694843453b7d743abab216bf81d5077b049b50427e6eacdac0f9dc35d1", "generation_seconds_batch": 16.75691494497005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13645529747009277, "target_z": -0.39453125142423495, "ce": 6.022613525390625, "genuineness": 4.645420074462891, "identity": 0.6073506474494934, "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/emo_Distress/a770bee00d49b442b497dd652591188e096e5d11aac9e0eb42554adfe808eafb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "a795bd27214ebed8e3b6f28fd013a5d51e3de21c3ff31412c71151e56b4d3edd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "7a7cb8660a4f9d24a0e07e5168587b536459731c5203c9d8e220c29d519b8ad2", "generation_seconds_batch": 20.402935312944464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0515944957733154, "target_z": 3.171874793770782, "ce": 5.704906940460205, "genuineness": 4.005263805389404, "identity": 0.1506032645702362, "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/emo_Distress/a795bd27214ebed8e3b6f28fd013a5d51e3de21c3ff31412c71151e56b4d3edd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "a7e4093082b87611763e11180638861c1f182c0d8b4656b0f94d5c69a02e4e27", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ac489c0223559dc689d5d5e8ad9804fc806daa81976553feef0814538cadd494", "generation_seconds_batch": 21.81522840098478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.005545437335968018, "target_z": -0.5546874857576507, "ce": 6.062326908111572, "genuineness": 4.362998008728027, "identity": 0.6238770484924316, "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/emo_Distress/a7e4093082b87611763e11180638861c1f182c0d8b4656b0f94d5c69a02e4e27.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "a83667a4cec9eb473cdb2267ad99f4aca4ec9ab3b9961c0c56c27af160448769", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3e2525ef4e159e1852e5dc0d8c60ab51566738369bbeffcb4dbc3b296a47e329", "generation_seconds_batch": 16.0166466179071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2214343547821045, "target_z": 2.1562498290918084, "ce": 5.990842819213867, "genuineness": 3.923675537109375, "identity": 0.5153981447219849, "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/emo_Distress/a83667a4cec9eb473cdb2267ad99f4aca4ec9ab3b9961c0c56c27af160448769.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "a8486339099625a08ae04837deffbe4c8ec7500ea15302720b40e06e0d0352ea", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4730621c2bf82f15d3e1b7a666cc3040ca3239cf24c78f4d7e721d608e5560b8", "generation_seconds_batch": 22.594514325028285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7195305824279785, "target_z": 2.765624982909181, "ce": 5.522225379943848, "genuineness": 3.6067352294921875, "identity": 0.10807058960199356, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. We kunnen er 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/emo_Distress/a8486339099625a08ae04837deffbe4c8ec7500ea15302720b40e06e0d0352ea.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "a87954778f5eda37f3cc824f8478cfd66d61ed7ecfbe839fed7222afae52a401", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "af56d3302f8b599f7c234db88506f48141c6b571501ab3c554e4acc5b398345b", "generation_seconds_batch": 22.091165601974353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15241992473602295, "target_z": -0.37499999088489644, "ce": 5.974957466125488, "genuineness": 4.319066047668457, "identity": 0.4597242474555969, "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/emo_Distress/a87954778f5eda37f3cc824f8478cfd66d61ed7ecfbe839fed7222afae52a401.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "a89a6f713db35d56e79753bc62335b962b5422bdf4422fe209c5968d10899b65", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9fe14388d3e8bc0fe8f94b5df7a2252a8226a93841586625552cb002752c219f", "generation_seconds_batch": 15.101821673102677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.538763701915741, "target_z": 0.09765626623627821, "ce": 6.205295085906982, "genuineness": 3.9299514293670654, "identity": 0.5468686819076538, "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/emo_Distress/a89a6f713db35d56e79753bc62335b962b5422bdf4422fe209c5968d10899b65.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "9b30969867f5b2be8b9ea8ff40677775a97d8941009a389368ca6c5755055e2b", "generation_seconds_batch": 17.474692296003923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.0305562019348145, "genuineness": 4.413206577301025, "identity": 0.6166843175888062, "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/emo_Distress/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "e7d1694f6c4d63c1b337c893f63bc6b69b4950123bd2c1346ae525ded2134eea", "generation_seconds_batch": 15.175397929968312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1588057577610016, "target_z": -0.3671875085454096, "ce": 6.300607204437256, "genuineness": 4.545003414154053, "identity": 0.6730431318283081, "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/emo_Distress/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "a9ce62c64ca04b52c8825f4a1bc84d71a77bf1dd396421460032c7fb94728e01", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7bd215d85f078995d14ce4e367dd27b6c9a30f4a313afa5a102a579b77f1b65c", "generation_seconds_batch": 16.311393729993142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 5.569881439208984, "genuineness": 3.553389072418213, "identity": 0.41278931498527527, "hypothesis": "The door is still open. I put your coat on the the chair. Tell me when you are ready.", "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/emo_Distress/a9ce62c64ca04b52c8825f4a1bc84d71a77bf1dd396421460032c7fb94728e01.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "a9f30904ed52b0048d4853b191a004fe9ef9b5a583e0c86de14a41fa2abfc318", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2f1639f79720b842e63c878779d2eabe58973d81ec39539f649eb3a08bd7dd25", "generation_seconds_batch": 16.581631037057377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.925107479095459, "target_z": 0.5703125233574529, "ce": 6.006728172302246, "genuineness": 4.218649387359619, "identity": 0.6052162647247314, "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/emo_Distress/a9f30904ed52b0048d4853b191a004fe9ef9b5a583e0c86de14a41fa2abfc318.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "aa5709389de8f96342cef49176b89a6b05a64058e5e4b2b0bf9ee4c744a35102", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "16a8e29425bd3084e11c597a56fb5227ff12f9a0039f24a2e43b982f073cd99c", "generation_seconds_batch": 22.456991170998663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9915440082550049, "target_z": 1.8750000273453107, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.5258563160896301, "hypothesis": "La puerta sigue. La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.2, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/aa5709389de8f96342cef49176b89a6b05a64058e5e4b2b0bf9ee4c744a35102.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "aad9e887b466495e402d61993fb9ac773c47db7d2d86b7cb0f627f9157f74660", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "c27b41e4026d4c3b5cc085ee472a004a2f92dd0a202d6b86ca32a8a7df6db51f", "generation_seconds_batch": 21.555205763084814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8005834221839905, "target_z": 0.4179687349031097, "ce": 5.764476776123047, "genuineness": 4.557555198669434, "identity": 0.7117466926574707, "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/emo_Distress/aad9e887b466495e402d61993fb9ac773c47db7d2d86b7cb0f627f9157f74660.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "aaf1b0851b9b41823be73cdf65770d3754157da147177473cea81a956a22e729", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "63dbb87c4af9b9ea847db3f984294bf18608560ae4863d0213ead2808549959e", "generation_seconds_batch": 23.218091547023505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0751749277114868, "target_z": 0.7539063140905718, "ce": 5.514282703399658, "genuineness": 3.8169827461242676, "identity": 0.3506574034690857, "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/emo_Distress/aaf1b0851b9b41823be73cdf65770d3754157da147177473cea81a956a22e729.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": "ab4f9e2467689aefe8e3050ef29bc89aeee2bf6cc6199802a0067fb5fe9a9bb4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "062993318d7cdd1874a0614dbf5d4ea3c01eea66c124915e485af61ef0c3881a", "generation_seconds_batch": 16.89073716197163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.064366340637207, "target_z": 3.187499977212241, "ce": 5.871703147888184, "genuineness": 4.20609712600708, "identity": 0.7095434665679932, "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/emo_Distress/ab4f9e2467689aefe8e3050ef29bc89aeee2bf6cc6199802a0067fb5fe9a9bb4.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "d83a9a26b13cdd8298fc2d4a74ffea4241ffcdfbe3a5bdd437917ceaf891ca00", "generation_seconds_batch": 14.356919717043638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25459349155426025, "target_z": -0.24999998176979288, "ce": 6.475345611572266, "genuineness": 4.162164688110352, "identity": 0.5153284072875977, "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/emo_Distress/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "abb7651269a9c5efe5d94c5d95e149c53dde6a78d1235bf4f0fc355466e02adc", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "166af3eac8d6d3ba325a333df03aff013c3f8f9cb753640d4a03fde560fca602", "generation_seconds_batch": 16.89073716197163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.655672073364258, "target_z": 2.687499940751827, "ce": 6.149696350097656, "genuineness": 4.394378662109375, "identity": 0.7834089994430542, "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/emo_Distress/abb7651269a9c5efe5d94c5d95e149c53dde6a78d1235bf4f0fc355466e02adc.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": "ac2ca58fe6a81f56046139aca5243a25e9e019373612e6d032df5e44cfbcb66a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0493cfeebb1c535ec9d94379b8b14aa8299ea3de93cfe58b9a3003a66efffe3", "generation_seconds_batch": 15.661036713048816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 5.617537498474121, "genuineness": 4.193545341491699, "identity": 0.7514932155609131, "hypothesis": "La route tourne à gauche après le pont continue. Je t'attendrai de l'autre côté.", "wer": 0.3, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/ac2ca58fe6a81f56046139aca5243a25e9e019373612e6d032df5e44cfbcb66a.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": "ac4c2b58caafeebeb0aabdfb9ceef4b774f85a533b2565f772df7787ec2d4239", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d6ad03571ff03ac3c661e87a62c22dbe2edc5907d197c153b40d32d754207e9", "generation_seconds_batch": 20.859526848071255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4640965461730957, "target_z": 2.453124814279765, "ce": 5.974957466125488, "genuineness": 4.005263805389404, "identity": 0.22827117145061493, "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/emo_Distress/ac4c2b58caafeebeb0aabdfb9ceef4b774f85a533b2565f772df7787ec2d4239.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": "ac707347887bb666d15d901eaebdc70445440518f9340cb6b74ddfa0fe07f4f2", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80e7b9bf0614e1cb7c084619a65e4ff9c59fb8bdbd8544f8812948cd7eb64d1a", "generation_seconds_batch": 17.04333790903911, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7871968746185303, "target_z": 1.6250000091151036, "ce": 5.831989288330078, "genuineness": 3.9425034523010254, "identity": 0.34198588132858276, "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/emo_Distress/ac707347887bb666d15d901eaebdc70445440518f9340cb6b74ddfa0fe07f4f2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "ac9c50c8c13c0d16352f2062a31d17cdaaa817df11d6f452127aab3163e9f542", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2d8f77927f255e9d9cff21db570d835a977c0ea852f3655a378e6a518a62afdf", "generation_seconds_batch": 21.776515208999626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6664806604385376, "target_z": 0.25390627763015766, "ce": 5.9431867599487305, "genuineness": 4.306513786315918, "identity": 0.49547839164733887, "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/emo_Distress/ac9c50c8c13c0d16352f2062a31d17cdaaa817df11d6f452127aab3163e9f542.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "accb71f33adaccdc044bbd18b613fdd02a59a407976dede8d34c8c934ab6c97a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9a018ec750d77b84c4677f610374130fa5d40051281dd5976bc6db96f7b464b8", "generation_seconds_batch": 23.41574717895128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37592458724975586, "target_z": -0.10156248917581452, "ce": 6.308549880981445, "genuineness": 4.645420074462891, "identity": 0.7177460193634033, "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/emo_Distress/accb71f33adaccdc044bbd18b613fdd02a59a407976dede8d34c8c934ab6c97a.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": "ad44176bbc8bbf48f8da1af63ce3df9e7121722143e21bc521de97cb4b36b427", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "95359124865122933acf8d7ba4327c3bd6fa1af495bf488bd1d2be0e20d04f0e", "generation_seconds_batch": 15.050857416004874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.919358730316162, "genuineness": 3.9173994064331055, "identity": 0.6644035577774048, "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/emo_Distress/ad44176bbc8bbf48f8da1af63ce3df9e7121722143e21bc521de97cb4b36b427.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "adb07fd854a11a96a1620a59cd4bc7102432d2f736ae39ca0910244e02b0e197", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c36631a896c865ae3cdf5c94a0df041694a1e442e0cf015e42678651c72fbfcc", "generation_seconds_batch": 19.999525881023146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1537680625915527, "target_z": 3.2968748028858856, "ce": 5.375286102294922, "genuineness": 3.9550557136535645, "identity": 0.5045565366744995, "hypothesis": "La porte est encore ouverte. J'ai. j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/adb07fd854a11a96a1620a59cd4bc7102432d2f736ae39ca0910244e02b0e197.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "adc2574745b2f79469ddc7b48e6bf06dc3a4dcbeddc40b07d46b2d9fe2ddc6b9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "838879d2fe07a3ffdcd36510f514492c1fd1f479a144e8aa96a116821d8db4ab", "generation_seconds_batch": 21.88226703298278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19392791390419006, "target_z": -0.3242187645271963, "ce": 6.070269584655762, "genuineness": 4.557555198669434, "identity": 0.6834004521369934, "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/emo_Distress/adc2574745b2f79469ddc7b48e6bf06dc3a4dcbeddc40b07d46b2d9fe2ddc6b9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "adc396d462e70145eb6e3588f7b82fdc5db4faba9e7f293cf06a81d03457acc8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f7d26fec8af91054abb5398bc8c3688aca9e6768919a0624d32d6db1b2120cb6", "generation_seconds_batch": 21.898009496042505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.370887041091919, "target_z": 3.5625000045575517, "ce": 4.601868152618408, "genuineness": 3.7667744159698486, "identity": 0.49967867136001587, "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/manual-comparison-v1/audio/emo_Distress/adc396d462e70145eb6e3588f7b82fdc5db4faba9e7f293cf06a81d03457acc8.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "d9aa9950dba362bb62914be666a7be94dd6391a1f1d9fcd94e2c33ced9e7600f", "generation_seconds_batch": 15.379623943008482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43659013509750366, "target_z": -0.027343742878825343, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.5401850938796997, "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/emo_Distress/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.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": "adeaab91a53fad76ddecad6c96d6bcf600e57abfa2a412526e050a58037499fe", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "31288012b2c22233f43c921b9c67a8d4081696b41df51fe9661068510b49fce9", "generation_seconds_batch": 16.261885207961313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.732302188873291, "target_z": 2.781249874667326, "ce": 6.24500846862793, "genuineness": 4.080576419830322, "identity": 0.5319430828094482, "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/emo_Distress/adeaab91a53fad76ddecad6c96d6bcf600e57abfa2a412526e050a58037499fe.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "4b251bfd5a2f83d6277cb64c4ac555974c2d623da7a5c1200f525816f1430140", "generation_seconds_batch": 17.414984659990296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 6.348263263702393, "genuineness": 3.9550557136535645, "identity": 0.22722099721431732, "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/emo_Distress/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "ae3964988bb1755bbdbfb2895be66e76b2ea61dac069aa299ed14157434fc696", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0e0446b4baa7bcc7ff6a4f89edc8300f2896089fd9c501d81bb391c5d4a34b27", "generation_seconds_batch": 22.076806891011074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4602887630462646, "target_z": 3.671874830231196, "ce": 5.534139156341553, "genuineness": 4.105680465698242, "identity": 0.4897450804710388, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/ae3964988bb1755bbdbfb2895be66e76b2ea61dac069aa299ed14157434fc696.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "ae74b67ce3adb24e114d51c2f07d70a4b6d22a379070c0645cd51893d4396a89", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "600b97810087df740c058bbcd2ea8c15f9636d9bd364b26d1a5182dcce3b4889", "generation_seconds_batch": 21.371548107941635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.425781488418579, "target_z": 2.4062498473220155, "ce": 5.935244083404541, "genuineness": 4.143336772918701, "identity": 0.4488786458969116, "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/emo_Distress/ae74b67ce3adb24e114d51c2f07d70a4b6d22a379070c0645cd51893d4396a89.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "aedd9f73631bbebde13008acd4b691d5f25218c3b96c4aa757c1269f5ce66677", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1e0f0a76eff40969008a5f86269f2b12ba0fc940a88cf5dad5f95ed7bdbdd2f0", "generation_seconds_batch": 21.555205763084814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10612252354621887, "target_z": -0.4316406245727295, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.46076083183288574, "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/emo_Distress/aedd9f73631bbebde13008acd4b691d5f25218c3b96c4aa757c1269f5ce66677.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "b06dcbb3c4eb80eabeb2a9394946112993c95d72348ee4ae33c4c4986997ee71", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "78c1988b6abe7afff458cd95e5578df960d2832492a1667d8627cd4951d5e675", "generation_seconds_batch": 20.54550458607264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.035015106201172, "target_z": 4.374999917964068, "ce": 5.577824115753174, "genuineness": 3.8671910762786865, "identity": 0.4473155736923218, "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/emo_Distress/b06dcbb3c4eb80eabeb2a9394946112993c95d72348ee4ae33c4c4986997ee71.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": "b09802a90bc66e8e2eff3b6c807cab21229aab9d13d68c6a3dfd3b1980ae4c20", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7b51320d543bcee2036188481fb2e0a84d2254d7be76a08ed888d1d9b0c7f7ae", "generation_seconds_batch": 20.515082628000528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5241472721099854, "target_z": 3.74999987238855, "ce": 5.824047088623047, "genuineness": 3.4592485427856445, "identity": 0.5609794855117798, "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": 0.03999999999999915, "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/emo_Distress/b09802a90bc66e8e2eff3b6c807cab21229aab9d13d68c6a3dfd3b1980ae4c20.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "b0b4400eff94a4ea0ec9c9ead38f075de7656f18a1823c2184ea495a1810cd4f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6caf62e289231c3db3113af41d948c1eefc28a39add25af446d6ae4e9c227d69", "generation_seconds_batch": 16.00180724496022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2443997859954834, "target_z": 0.9609374424609087, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.8364382982254028, "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/emo_Distress/b0b4400eff94a4ea0ec9c9ead38f075de7656f18a1823c2184ea495a1810cd4f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "b123f9c91499fc9698b6b679bf876630dc56b4cbf253126f26377a82010fd96e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "859e189beae7c62cd69c890a0c6f1c0f679b85c57c2260481cd3fc74cbdbbdba", "generation_seconds_batch": 20.767590621951967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15561282634735107, "target_z": -0.37109376794536014, "ce": 6.197352409362793, "genuineness": 4.595211505889893, "identity": 0.7188260555267334, "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/emo_Distress/b123f9c91499fc9698b6b679bf876630dc56b4cbf253126f26377a82010fd96e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "b1464515d821a00eb4502818b2c01ed7710e5f6c3d8226f09e973b8783fea33e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0a50916517eb23ffa8f1845beee241f5a504621ebf5de763e32fe8e04d58c70f", "generation_seconds_batch": 16.481014234013855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591813564300537, "target_z": 2.609374898594473, "ce": 6.125868320465088, "genuineness": 3.9927117824554443, "identity": 0.48536407947540283, "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/emo_Distress/b1464515d821a00eb4502818b2c01ed7710e5f6c3d8226f09e973b8783fea33e.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": "b19c46c2c45227c2f624889c9712666335b2ad13a5babbd6431255d657c030fc", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa28d909c5820508b792f6d93a093eee27caf8171abc030ed479b25f4057fb93", "generation_seconds_batch": 22.38718523096759, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8344757556915283, "target_z": 2.9062498837824298, "ce": 5.696964263916016, "genuineness": 3.8797430992126465, "identity": 0.7279471158981323, "hypothesis": "Quelqu'un déplaçait la petite chaise bleue. Elle était ici. Près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "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/emo_Distress/b19c46c2c45227c2f624889c9712666335b2ad13a5babbd6431255d657c030fc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "b1ac16e2cb0108acdfc99d895d5943b71c65011b99a5051c5d9f4181447e0d62", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ca824ed95afd452229c5b889738a39bff56dc418909e70ea68292cf5c37eea23", "generation_seconds_batch": 22.225947962026112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2114890068769455, "target_z": -0.3027343742878825, "ce": 6.2767791748046875, "genuineness": 4.557555198669434, "identity": 0.39472368359565735, "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/emo_Distress/b1ac16e2cb0108acdfc99d895d5943b71c65011b99a5051c5d9f4181447e0d62.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": "b1c5726c1763da2d14611db96707bc7c5cc3470cb7b71980226beea1f2135313", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd000b3490781b10749f4f1ba3fc97fbcab50f829d7d93424fdf1558a36e955b", "generation_seconds_batch": 22.33743581699673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.064366340637207, "target_z": 3.187499977212241, "ce": 5.569881439208984, "genuineness": 3.848362922668457, "identity": 0.5010442733764648, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter. Bis zu dem kleinen Holztor. Ich werde 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/emo_Distress/b1c5726c1763da2d14611db96707bc7c5cc3470cb7b71980226beea1f2135313.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b25ef4d03fa950bd568f57e9d1e1d7f9784b6d2bf64b78bbff55f0962c106120", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ffccbf8ee0b4e108ac660e2f253948df209e4e006920c39e3ca8eb4b750a6d56", "generation_seconds_batch": 21.71621317602694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.421973705291748, "target_z": 3.624999863273447, "ce": 5.609594821929932, "genuineness": 3.8546390533447266, "identity": 0.21334943175315857, "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/emo_Distress/b25ef4d03fa950bd568f57e9d1e1d7f9784b6d2bf64b78bbff55f0962c106120.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b2ba2e744cb2bda59fb96ca8c4acc57e8f3e9b57392398d3473d3dabb5d0ba4d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "58a085e57360a96206c73079f66e6a68b7b572782c4d1416863a15da59a7b081", "generation_seconds_batch": 23.096612227032892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0298590660095215, "target_z": 1.9218749943030602, "ce": 5.2918877601623535, "genuineness": 3.7416701316833496, "identity": 0.1031244769692421, "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/emo_Distress/b2ba2e744cb2bda59fb96ca8c4acc57e8f3e9b57392398d3473d3dabb5d0ba4d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "b2c88597ae741f3e58aacc4728b8ed36f0fbc8697a5ef87c0497b3cfb43c9a06", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a14b1f36719df7d656337e1904b5a539d539b523e0f86633ad44fe39d092307d", "generation_seconds_batch": 15.97321290790569, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5062196254730225, "target_z": 1.2812500569693972, "ce": 5.752562999725342, "genuineness": 4.507347106933594, "identity": 0.6371793746948242, "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/emo_Distress/b2c88597ae741f3e58aacc4728b8ed36f0fbc8697a5ef87c0497b3cfb43c9a06.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": "b2d791979a1f84519e9a65d86e154df0e942c5bce2535a80a0f857ca04c87a21", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d14ca8b879fdfd991e5db4a6ba397621c80799f65da33ccfd8cf09a7278ab6e", "generation_seconds_batch": 21.67797936697025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.821704149246216, "target_z": 2.8906249920242844, "ce": 5.780362129211426, "genuineness": 3.8922953605651855, "identity": 0.25796371698379517, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge boekenkast. We zetten het naar de lunch terug.", "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/emo_Distress/b2d791979a1f84519e9a65d86e154df0e942c5bce2535a80a0f857ca04c87a21.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "b36160ebaaa08509b59c420f9fc260cf5bc7d32277896345f3cb1fdfc881523f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "91e501348515b2ef4bf66c3ca7b44976b9185a233995c58d89174f1704137a0c", "generation_seconds_batch": 22.614740025950596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4385533332824707, "target_z": 2.4218750307634744, "ce": 5.911416053771973, "genuineness": 4.281409740447998, "identity": 0.3730756938457489, "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/emo_Distress/b36160ebaaa08509b59c420f9fc260cf5bc7d32277896345f3cb1fdfc881523f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "b381c69e83f006f2f7fd7a232b266ac96910a48c61a9c8abf70b8c185f5dd85d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c7b6b0c874536d9c1235ef5ef5bc5e28c67b0cd3a9ae756d2401b5f17b43efa7", "generation_seconds_batch": 15.39896497700829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.421973705291748, "target_z": 3.624999863273447, "ce": 5.71682071685791, "genuineness": 4.319066047668457, "identity": 0.6382676959037781, "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/manual-comparison-v1/audio/emo_Distress/b381c69e83f006f2f7fd7a232b266ac96910a48c61a9c8abf70b8c185f5dd85d.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "0d99e064beef3e9e4d27aae468c028a59317a88851f893b157f9abc60e8792c7", "generation_seconds_batch": 17.173563727061264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10931545495986938, "target_z": -0.42773436517277896, "ce": 6.38797664642334, "genuineness": 4.306513786315918, "identity": 0.4934108257293701, "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/emo_Distress/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "b445ec6dbac0efd035ea70ceb9a2670c93cdb2f43081803bbc350321792b1aca", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cac685f67d9b81622417bd739ac6e449033945da39a7eb03de9e5771e43215dc", "generation_seconds_batch": 15.5343606879469, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3210300207138062, "target_z": 1.054687522218065, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.6850757598876953, "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/emo_Distress/b445ec6dbac0efd035ea70ceb9a2670c93cdb2f43081803bbc350321792b1aca.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "b45169451715d0f7f110a4c29f7b4597814b05bd7b1609ca6eaac0a68ef51292", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8881da2c764031488daffd5af1eb80f0d22634114330160ebfa3261132d4b352", "generation_seconds_batch": 23.227101668016985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8133550882339478, "target_z": 0.43359369958208344, "ce": 5.919358730316162, "genuineness": 4.720732688903809, "identity": 0.36046546697616577, "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/emo_Distress/b45169451715d0f7f110a4c29f7b4597814b05bd7b1609ca6eaac0a68ef51292.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "b4d1011257ef529fa960cc88101c5dce3a23c135906d7da8c04e02d206404837", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7cf6ae310dbebd93612a2ee16e86db0694192b98a3be6bf03e9b9f94e5515c18", "generation_seconds_batch": 15.060581807047129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5534985065460205, "target_z": 2.562499931636723, "ce": 5.839932441711426, "genuineness": 4.118232727050781, "identity": 0.5531943440437317, "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/manual-comparison-v1/audio/emo_Distress/b4d1011257ef529fa960cc88101c5dce3a23c135906d7da8c04e02d206404837.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b4f520f37b5cbb467993252037cc6fbec191a1263e0417d90bdfb605b05c6d4b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "c354a654d89c4b0f3a732b2de9bf079952cdd2f3fb878e91163af30b31744e89", "generation_seconds_batch": 19.85605293698609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5611141324043274, "target_z": 0.12499997265468932, "ce": 6.062326908111572, "genuineness": 4.080576419830322, "identity": 0.8151435852050781, "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/emo_Distress/b4f520f37b5cbb467993252037cc6fbec191a1263e0417d90bdfb605b05c6d4b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "b51b66c260d49a822f003e60024d94ad3e38f64a9e82ba753c8dec03365cb80c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "630ef4063bd2749229fed79fb5bebbf6e563b62ac72718e5ecce39db057044c1", "generation_seconds_batch": 20.553937393939123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6045851707458496, "target_z": 2.6249997903526183, "ce": 5.824047088623047, "genuineness": 3.9927117824554443, "identity": 0.4735430181026459, "hypothesis": "Ik heb het het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er 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/emo_Distress/b51b66c260d49a822f003e60024d94ad3e38f64a9e82ba753c8dec03365cb80c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b5c836d8bdb8f8478ae6f7b7177675400e338c2da18b469f74710672ac11d9c1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "65598fab77acceae0445d852119642f51a772503564adb264fa5953f0657ad4f", "generation_seconds_batch": 24.51323902606964, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5509204864501953, "target_z": 1.3359374698062194, "ce": 5.982900142669678, "genuineness": 3.9425034523010254, "identity": 0.6671553254127502, "hypothesis": "De deur staat nog open. Ik heb je 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/emo_Distress/b5c836d8bdb8f8478ae6f7b7177675400e338c2da18b469f74710672ac11d9c1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "b71590bbbea7ac6ac42698a89e77bc59bda272b24ce84141bdac6a16a41e7084", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "48e5c87fb0348f2b9e6c393e9e07e6e1d2b9e5f57c3a46e5feeb9c8bad4e4f60", "generation_seconds_batch": 22.070430728956126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787722826004028, "target_z": 1.8593749897455085, "ce": 6.006728172302246, "genuineness": 4.218649387359619, "identity": 0.5906425714492798, "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/emo_Distress/b71590bbbea7ac6ac42698a89e77bc59bda272b24ce84141bdac6a16a41e7084.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b75659a3595a430d23aa7d58bd03d6e962e670ff30fd6b0559ea6f59fef82203", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "418008e1d33ac5a00736b73e2324dac70fa6c7f8e5c753d8015574e9841638e9", "generation_seconds_batch": 22.95398238301277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3401875495910645, "target_z": 1.0781250056969398, "ce": 5.879645347595215, "genuineness": 4.111956596374512, "identity": 0.2187381535768509, "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/emo_Distress/b75659a3595a430d23aa7d58bd03d6e962e670ff30fd6b0559ea6f59fef82203.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "b7bb170c6c24adc26746da58f13e4972dba18bdaecb815668594c8367d7d8938", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "80d6f0fc07ee52a5e721cddda62d22a962670048d5a780b7a2025638cfad41cd", "generation_seconds_batch": 15.956516021047719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27854040265083313, "target_z": -0.22070312742119938, "ce": 6.109982967376709, "genuineness": 4.105680465698242, "identity": 0.6694033145904541, "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/emo_Distress/b7bb170c6c24adc26746da58f13e4972dba18bdaecb815668594c8367d7d8938.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "b7e090da3146126992551be329febda03dc43aec2364c79d488b4ed3edf20868", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "753d392fdcea640c4244d98c2abd1590ab254c75fd4fbb10c327dbac69dde712", "generation_seconds_batch": 20.72976193507202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42222195863723755, "target_z": -0.04492189194839568, "ce": 5.9431867599487305, "genuineness": 4.457139015197754, "identity": 0.2903865575790405, "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/emo_Distress/b7e090da3146126992551be329febda03dc43aec2364c79d488b4ed3edf20868.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "b8223baa99b56512eef86f6686abbaa9f31b191f9884835abcac194f85c9969c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "01688713b8ca996f43288e345d82334314fff310f1c1fdd0212f162a925b3954", "generation_seconds_batch": 21.592975814943202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5764639377593994, "target_z": 1.3671875450058237, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.8031003475189209, "hypothesis": "La porte est encore ouverte. J'ai posé. j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/b8223baa99b56512eef86f6686abbaa9f31b191f9884835abcac194f85c9969c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "b8fed0b8573676c9a8613a1f6edf99ab49f6074c4fc5ed269943c65468daa436", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b570aec610805c31505c4d15a48de00a928e3345e613d07f1576419524c59d42", "generation_seconds_batch": 23.10077690402977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.903473377227783, "genuineness": 4.13078498840332, "identity": 0.1016390472650528, "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/emo_Distress/b8fed0b8573676c9a8613a1f6edf99ab49f6074c4fc5ed269943c65468daa436.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": "b986c9de79d820fb094426222adaa32904f3894ca04551011e10b94949fe27a4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b788d0942ece8013a070a8d9d7e5642dbdc216d7ee646ba39239ce46c39ed561", "generation_seconds_batch": 15.300253112916835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9021421670913696, "target_z": 1.7656250558300093, "ce": 5.6532793045043945, "genuineness": 4.061748504638672, "identity": 0.6392762064933777, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai accardé dans le tiroir, puis près de la fenêtre. Prends l'écran, tu partiras.", "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/emo_Distress/b986c9de79d820fb094426222adaa32904f3894ca04551011e10b94949fe27a4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "b9fac54736b627a0f480f67a1463aa9cea1978638e3b9c8129c9928e4b303570", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "523061b6e09a704a62187e87dd77e6d6c1cdd61eb7d3f10952706a9f7df0d168", "generation_seconds_batch": 22.559945516986772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2641722559928894, "target_z": -0.23828124003035547, "ce": 6.2767791748046875, "genuineness": 4.7458367347717285, "identity": 0.3273703157901764, "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/emo_Distress/b9fac54736b627a0f480f67a1463aa9cea1978638e3b9c8129c9928e4b303570.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": "ba3f71485f34a7f04cd3fe9a76498797bd6c95f0b3aadf2c5b2d3b04939c8a47", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a977624865805473e5a8d9ceb43efd3da0824f0bdd7bc253574d3355641d31c7", "generation_seconds_batch": 22.33743581699673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 5.319687366485596, "genuineness": 3.8922953605651855, "identity": 0.5378894805908203, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter. Bist du den kleinen Holztor? Ich warte auf der anderen Seite.", "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/emo_Distress/ba3f71485f34a7f04cd3fe9a76498797bd6c95f0b3aadf2c5b2d3b04939c8a47.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": "ba476df97ce7f2be9c3aecda20d897c5f74d632fd1c58ffdb6a618e5832b7637", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d785d70014c03a9c7d0a94eb8fa25a117fd995f2757a2a5b5d0d5e3d9fc683c", "generation_seconds_batch": 16.99001612898428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0043156147003174, "target_z": 1.8906249191034559, "ce": 5.685050010681152, "genuineness": 4.231201171875, "identity": 0.7416560649871826, "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/emo_Distress/ba476df97ce7f2be9c3aecda20d897c5f74d632fd1c58ffdb6a618e5832b7637.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "41d896dcc50014c9f01af9d6c06e1374ac0c6605c8482eceb5b6ce9155118db2", "generation_seconds_batch": 17.333966215956025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.165581703186035, "genuineness": 4.65797233581543, "identity": 0.8078435659408569, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis, près de la fenêtre. Prends l'écran, tu partiras.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "ba7a8824bd33adacda7bfbfc51eedcfd3368ba08074aa29d95b3c812231ecf05", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "47f4e46a506a168bf3655f014e4ad25b0eac613950a9dc8cdd1edd3eddbcfdf6", "generation_seconds_batch": 14.948860263917595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28811919689178467, "target_z": -0.20898434922134776, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.42895543575286865, "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/emo_Distress/ba7a8824bd33adacda7bfbfc51eedcfd3368ba08074aa29d95b3c812231ecf05.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "ba9d421eee3fa15255472f9c416e7fec84b79c2fa84f74dcb93da5370e8d1ad9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "92e8efea5f4bb220e694319090f8fba19958176ccbe12cf4061ccc3bf34598c1", "generation_seconds_batch": 21.91172292898409, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.213237762451172, "genuineness": 4.319066047668457, "identity": 0.49907612800598145, "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/emo_Distress/ba9d421eee3fa15255472f9c416e7fec84b79c2fa84f74dcb93da5370e8d1ad9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "baa1a6452e906fa9513405100157138d932184af1225d83747561116477d68d1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8d0028b7c8afe4272194c29f853596f00a1ac9adef7219f209282185c938810d", "generation_seconds_batch": 21.661893568001688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1731739342212677, "target_z": -0.34960935947583927, "ce": 6.086154937744141, "genuineness": 3.860914945602417, "identity": 0.5354515910148621, "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/emo_Distress/baa1a6452e906fa9513405100157138d932184af1225d83747561116477d68d1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "baaf9cc6fe9b1a36d8e704ef12e5626c15ca3d14f48c0ff1f40b8bc9335414ce", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6e83cb7b2583e122cf9f366577fa6d59abf546d622aa265061863845248cb5bf", "generation_seconds_batch": 16.820383492973633, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5223999619483948, "target_z": 0.07763672782949768, "ce": 5.967014789581299, "genuineness": 4.231201171875, "identity": 0.7147268056869507, "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/emo_Distress/baaf9cc6fe9b1a36d8e704ef12e5626c15ca3d14f48c0ff1f40b8bc9335414ce.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "bbbbeebfeb95beaf859534400600a0f93029b56842c162091b997649056481a0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "48c033c9399ff66bbd4d5716f4dfb77eb6cfd558224576d6cc270985279e9406", "generation_seconds_batch": 20.451534943073057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4423611164093018, "target_z": 1.2031250148120434, "ce": 5.967014789581299, "genuineness": 3.973883628845215, "identity": 0.7450123429298401, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude ramen. We kunnen er 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/emo_Distress/bbbbeebfeb95beaf859534400600a0f93029b56842c162091b997649056481a0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "bbdefa5cc40ab57d724352efe4692921b33a274eaf019c733582ea897a6ae552", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "9cde15b5e881816e1cb0ee0b5181538df9f660d09662938c48e580e4030568f2", "generation_seconds_batch": 17.63829254102893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0809457302093506, "target_z": 1.984374853018955, "ce": 5.77639102935791, "genuineness": 3.9550557136535645, "identity": 0.48103588819503784, "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/emo_Distress/bbdefa5cc40ab57d724352efe4692921b33a274eaf019c733582ea897a6ae552.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "bc0ef37c117c1d06772bf2da833dc2d0d1cc020c42709c3234e440e668f203aa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0b58e362b030f2ca1aaae19b3310d9a6b01ff237eac048e25ed9e727cbee2d85", "generation_seconds_batch": 13.929408598109148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24022531509399414, "target_z": -0.2675781308393632, "ce": 6.046441555023193, "genuineness": 4.796044826507568, "identity": 0.700549840927124, "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/emo_Distress/bc0ef37c117c1d06772bf2da833dc2d0d1cc020c42709c3234e440e668f203aa.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": "bc8897b60cd9690d9e00f12994e05fbea0320c975ca80f533526fd43e0dff332", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b1c7d0299fc8d7843538857ed5bcf37417c20ddd1ee195150c6171affbabf8f0", "generation_seconds_batch": 15.050857416004874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1920831203460693, "target_z": 3.343749769843635, "ce": 5.80021858215332, "genuineness": 3.9299514293670654, "identity": 0.4768638610839844, "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/emo_Distress/bc8897b60cd9690d9e00f12994e05fbea0320c975ca80f533526fd43e0dff332.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "bcccfc78de6f36ac3ab2a6ec6d7232cd09dad7b327bc21166a5afe1e6a74c28e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f43f00dbe4f3f6e509f852d25270660e85d91ef8eb515183ed6a587fa9b3b0c", "generation_seconds_batch": 22.95398238301277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8804064989089966, "target_z": 0.5156249646789737, "ce": 5.796247482299805, "genuineness": 3.9299514293670654, "identity": 0.45543521642684937, "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/emo_Distress/bcccfc78de6f36ac3ab2a6ec6d7232cd09dad7b327bc21166a5afe1e6a74c28e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "bcf46706e68802517b24f3f84a5236dce8773aad265da561a7e9a77524e5d06d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "42dcf2d6720ab661bf51fd0361d99910ab0c1411e2c3317d5d2df4ff3e3dff5e", "generation_seconds_batch": 22.369824975030497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7878117561340332, "target_z": 0.40234377022413603, "ce": 6.0146708488464355, "genuineness": 4.419482707977295, "identity": 0.5206601619720459, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/bcf46706e68802517b24f3f84a5236dce8773aad265da561a7e9a77524e5d06d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "bd04e2044af59f467ad4968f193d6a17b7b9f1474985e6b4076e0bfacd12cbfe", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "5be3a23e71358c4bb4fa560352d4a53272fcbc7d8988f1cfe62cd0190dee93b0", "generation_seconds_batch": 20.848301346995868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2214343547821045, "target_z": 2.1562498290918084, "ce": 5.863759994506836, "genuineness": 4.250029563903809, "identity": 0.43706077337265015, "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/emo_Distress/bd04e2044af59f467ad4968f193d6a17b7b9f1474985e6b4076e0bfacd12cbfe.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "bd2e842f53b25944875ada92719455fd1760a5082bcd833a3756a97b7055eb42", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1e9b26da321d29b597ff8eb4bdecd354d761ae860091962c1f27c9214e136fcc", "generation_seconds_batch": 15.995918376953341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9660006761550903, "target_z": 1.8437500979873633, "ce": 5.903473377227783, "genuineness": 4.557555198669434, "identity": 0.7725912928581238, "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/emo_Distress/bd2e842f53b25944875ada92719455fd1760a5082bcd833a3756a97b7055eb42.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": "bdddbb9ce97b68781395608d8704eb4fcaf2cbbb94d55f56303e9f8e460c4199", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9909fcfb0a00151de33500731e4909a9e0cbad6cf384f9b447df7b5976cc3b1d", "generation_seconds_batch": 16.659622146980837, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7706172466278076, "target_z": 2.8281248416250757, "ce": 6.006728172302246, "genuineness": 3.936227321624756, "identity": 0.5496386289596558, "hypothesis": "La route tourne à gauche après les ponts. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/bdddbb9ce97b68781395608d8704eb4fcaf2cbbb94d55f56303e9f8e460c4199.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "be365e9bf3cf50305545c52f6e8e4f86db49d373595b5ab5b31bda3e1454167e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "89a471eb0fd9bc473ab20f59e010770f5deb2fd80433e5241739353224749a18", "generation_seconds_batch": 20.44515813200269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7999686002731323, "target_z": 1.6406250467149057, "ce": 5.506340026855469, "genuineness": 4.494794845581055, "identity": 0.4363899528980255, "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/emo_Distress/be365e9bf3cf50305545c52f6e8e4f86db49d373595b5ab5b31bda3e1454167e.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": "be5e1b04bd93378448abf021fd8aa22aa50d2e67e18f6f198295863f0cf84a60", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aebd9f29fbda591dd25a7049da5b242b4c195a9e2363788db4af5b3021eb0cb6", "generation_seconds_batch": 15.142696383991279, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8817546367645264, "target_z": 4.187499758449755, "ce": 5.530168056488037, "genuineness": 3.7165660858154297, "identity": 0.3286020755767822, "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/emo_Distress/be5e1b04bd93378448abf021fd8aa22aa50d2e67e18f6f198295863f0cf84a60.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "be90d970819ae1f2223838a45cd347bfe5468b9986e7975a5cc109e58f260ebc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "24979f39905ffc0c6523f14a82576280f83ca1406d9a7ee0a0802c4e6e18bdc7", "generation_seconds_batch": 23.988783151027746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2801368832588196, "target_z": -0.218749979491017, "ce": 6.2767791748046875, "genuineness": 4.18099308013916, "identity": 0.13598960638046265, "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": 0.03999999999999915, "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/emo_Distress/be90d970819ae1f2223838a45cd347bfe5468b9986e7975a5cc109e58f260ebc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "bebc1c24a78338c559b2c00e685feff3843fbc39302cf2e8d314566255448c04", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4215ca8b2bca64d22f7474fb6555e5e6b17574de2c919a475b9fd3d8c0e07136", "generation_seconds_batch": 22.369824975030497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9532289505004883, "target_z": 1.8281250603875612, "ce": 5.514282703399658, "genuineness": 4.086852550506592, "identity": 0.4473983645439148, "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/emo_Distress/bebc1c24a78338c559b2c00e685feff3843fbc39302cf2e8d314566255448c04.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "bfbee55e9e87a42eb4bc5324cdbce3200bbc7a7f0d0bcec1936e8e5b165ec5f7", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9ce2b5873148d6c6a87565f398327fb829c9c95a00e726052747397dd7624af9", "generation_seconds_batch": 22.358313245000318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5381488800048828, "target_z": 1.3203125780480742, "ce": 5.95112943649292, "genuineness": 4.457139015197754, "identity": 0.33366137742996216, "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/emo_Distress/bfbee55e9e87a42eb4bc5324cdbce3200bbc7a7f0d0bcec1936e8e5b165ec5f7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "bfdd4dd29429ee788eb8e27d30244f503fdd84555e6913345a9753a568e4c235", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5dc0448372020a4fc28444c2ebed5e21a02d43a6490c1cab3bda2eae7106e031", "generation_seconds_batch": 17.402943643042818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12528005242347717, "target_z": -0.40820314109385475, "ce": 5.824047088623047, "genuineness": 4.193545341491699, "identity": 0.5366919040679932, "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/emo_Distress/bfdd4dd29429ee788eb8e27d30244f503fdd84555e6913345a9753a568e4c235.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "c0f14a2be0ca676edb52bcd9d19d3cf34042ddaba67e0828ddacf58e9c64805b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0107d87e49dfc34dc5b1f9b86225e1e823e57717ae4e2105a06688550b7ebc1a", "generation_seconds_batch": 20.848301346995868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.706758737564087, "target_z": 2.7499997994677217, "ce": 5.303802013397217, "genuineness": 3.9550557136535645, "identity": 0.02111774869263172, "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/emo_Distress/c0f14a2be0ca676edb52bcd9d19d3cf34042ddaba67e0828ddacf58e9c64805b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "c2e7c71b5e1f6cb17eba8adbc6e160d1f2f5743c11c72431cf59a7458ab3a7cc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "fa53a8b3520d8af0d24e8c350bda0fab9eb2e65f852c631d643c1362fc25ec8e", "generation_seconds_batch": 20.23061308299657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8740206956863403, "target_z": 0.5078125187999011, "ce": 6.046441555023193, "genuineness": 4.770940780639648, "identity": 0.6314288377761841, "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/manual-comparison-v1/audio/emo_Distress/c2e7c71b5e1f6cb17eba8adbc6e160d1f2f5743c11c72431cf59a7458ab3a7cc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "c325784fe470dfc04fc520d97ff064b77f3462878c46fd2358595e0c3bd2f7d1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "760f4ff26151f9eb7e655e937f61c1e528369e64c8864fbbea0564877be443d0", "generation_seconds_batch": 20.76595830998849, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1026813983917236, "target_z": 3.2343749441699905, "ce": 5.307773113250732, "genuineness": 3.823258876800537, "identity": 0.20797857642173767, "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/emo_Distress/c325784fe470dfc04fc520d97ff064b77f3462878c46fd2358595e0c3bd2f7d1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "c37c515fc45d95fbf0c59fe6ddca71196975d06ab1da4c68bce84d9423d22e2c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5a75cf14c0bad57d971ebd1ed3bb2f96a15266b3964f2714b57d9bb91f8c10c5", "generation_seconds_batch": 22.27198200300336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.068174123764038, "target_z": 1.96874996126081, "ce": 5.8875885009765625, "genuineness": 4.143336772918701, "identity": 0.46479886770248413, "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/emo_Distress/c37c515fc45d95fbf0c59fe6ddca71196975d06ab1da4c68bce84d9423d22e2c.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "45217aead2444d16141f16984f5e8ecbb424b73658bd100cd64c1b5958113b9e", "generation_seconds_batch": 17.135520527954213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19392791390419006, "target_z": -0.3242187645271963, "ce": 6.046441555023193, "genuineness": 4.519899368286133, "identity": 0.6383285522460938, "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/emo_Distress/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "c3c65ce35c777531742445f35255efd1c14c9db20982829502ff13bddfee0f84", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2fe138aff82c777d7f3310503c5a1650b3a50ec24eb7975e6e972f6a0a5aadf8", "generation_seconds_batch": 22.957366917049512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5818681716918945, "target_z": 0.15039064052416076, "ce": 5.974957466125488, "genuineness": 4.268857479095459, "identity": 0.4540119767189026, "hypothesis": "He encontrado la cajita. Estaba junto, junto a la ventana. Vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/c3c65ce35c777531742445f35255efd1c14c9db20982829502ff13bddfee0f84.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": "c3d13d3ed0a541df758990677401888f58d8ace46e52a0e364b56330ba091e27", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7b64ca4eee04d62058ec8b7da8a6a39f1b6777b95140db105d18b1775b968f4", "generation_seconds_batch": 21.585045735933818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 5.728734970092773, "genuineness": 4.042920112609863, "identity": 0.672670841217041, "hypothesis": "Jemand hat kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir standen ihn laut dem Essen zurück.", "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/emo_Distress/c3d13d3ed0a541df758990677401888f58d8ace46e52a0e364b56330ba091e27.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": "c411b6d1238eb65b74a10da627380b30a8c703f9c5af95a57d0a223a8e34f0b0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18131dd70579fb81daedcd61294d09afe534b9d8cb91855b71243f59091e1fd1", "generation_seconds_batch": 18.187164644012228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.772419452667236, "genuineness": 3.835810661315918, "identity": 0.6826434135437012, "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/emo_Distress/c411b6d1238eb65b74a10da627380b30a8c703f9c5af95a57d0a223a8e34f0b0.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "311d5af957fd52ab41185133a1fd21b290e5b9c4d572b2ef3b0f9098a652a29c", "generation_seconds_batch": 13.576297940104268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.8353389501571655, "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/emo_Distress/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "c5d0866408f7e9a5fec8d1ff7cab038513fa9cbeb7c106856b41a0dbcc6456aa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "61a3456d6424aa5f33f9110643fba15fb835857ea461d602e4c966b6c029e894", "generation_seconds_batch": 21.450732139055617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8063544034957886, "target_z": 1.6484374925939784, "ce": 6.022613525390625, "genuineness": 4.262581825256348, "identity": 0.32515546679496765, "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/emo_Distress/c5d0866408f7e9a5fec8d1ff7cab038513fa9cbeb7c106856b41a0dbcc6456aa.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "c5e7461a5fddfb0e875712ac201cda213a17f8403dac38ca9dccc6158949261e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "405ec8fa950dd11437f16c575caceb46b87fdbbfcb9fd19826f6bc421952a241", "generation_seconds_batch": 21.836037456057966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9532289505004883, "target_z": 1.8281250603875612, "ce": 6.229123115539551, "genuineness": 4.017816066741943, "identity": 0.529916524887085, "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": 0.03999999999999915, "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/emo_Distress/c5e7461a5fddfb0e875712ac201cda213a17f8403dac38ca9dccc6158949261e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "c6076c653528b61eae11048ed0fe29d2934bf4a65470d76ec2a2377029e645a2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "dfed892ae6df66891970fecbfb39301d80b5dc66d6a58d5ab4dc360efca1a413", "generation_seconds_batch": 22.11987629206851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.566270112991333, "target_z": 2.5781248233948686, "ce": 5.990842819213867, "genuineness": 4.319066047668457, "identity": 0.5150467753410339, "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/emo_Distress/c6076c653528b61eae11048ed0fe29d2934bf4a65470d76ec2a2377029e645a2.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": "c6823af51a0e3d18714f9cbb6cf2d35e3316184b3f60cad2e589b3f4e9e46a5b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d8fe40290d7f117b0c5f6b24fab57a7da139f52ac2200ef2b970a7d10d3535e", "generation_seconds_batch": 15.62638532789424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.43088436126709, "genuineness": 3.7667744159698486, "identity": 0.5139179229736328, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier in dem hohen Bücherregal. Er wäsche ihn nach dem Essen zurück.", "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/emo_Distress/c6823af51a0e3d18714f9cbb6cf2d35e3316184b3f60cad2e589b3f4e9e46a5b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "c690ac8563cebec7f3d4330ea46350b13c6d496facd6010c98a8a4ca79ebcd32", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b2bc78225d7dc029d3fe572f7c01f51603e3fc8b8aee0541e6a48ed44455e1fa", "generation_seconds_batch": 18.994405148085207, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5004485845565796, "target_z": 0.050781226357700146, "ce": 5.593709468841553, "genuineness": 4.168440818786621, "identity": 0.19148923456668854, "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/emo_Distress/c690ac8563cebec7f3d4330ea46350b13c6d496facd6010c98a8a4ca79ebcd32.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "c7765ee5964fb5c0c42bd2b97bc5e915afede173e1d8ed40cf33321309630d8e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "68060d893e40e4a99e3eca6355ef3b30d7106f56aaf69182af5307797ad2dae7", "generation_seconds_batch": 21.422422431991436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.706758737564087, "target_z": 2.7499997994677217, "ce": 5.295859336853027, "genuineness": 3.835810661315918, "identity": 0.6524023413658142, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/c7765ee5964fb5c0c42bd2b97bc5e915afede173e1d8ed40cf33321309630d8e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "c797d7b1e1a53259b590c4d81099bb94a4b591f23c9b021d0ccf57b088683fbe", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "118edab60d73d89a3366f5c0cd9e1f276d15feaceecfb7c2e8ca06d6bd1297bd", "generation_seconds_batch": 21.633088954957202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1588057577610016, "target_z": -0.3671875085454096, "ce": 6.316492557525635, "genuineness": 4.18099308013916, "identity": 0.48315203189849854, "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/emo_Distress/c797d7b1e1a53259b590c4d81099bb94a4b591f23c9b021d0ccf57b088683fbe.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "c7f8bc1e54fa88d388271e73b7ef543040208a24cc6c124a4002820e6a40eb96", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8dfa0d39bdea5ebc3f5cfe14d34548a0e7fc4db9d5ce83503b9d0488b5e4d8c9", "generation_seconds_batch": 14.52448257803917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6090080142021179, "target_z": 0.1835937542727048, "ce": 6.340320587158203, "genuineness": 4.7458367347717285, "identity": 0.6719957590103149, "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/emo_Distress/c7f8bc1e54fa88d388271e73b7ef543040208a24cc6c124a4002820e6a40eb96.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "c80780146567765d1be8f9298c7fcc1bb3035b7e2768e4a3e6ae4fc9638b0999", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "19452c5243f8983ba702470949c4afbcbd1f61ae7a892796b9e089d366f7df6e", "generation_seconds_batch": 24.13925038801972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16040223836898804, "target_z": -0.3652343606152272, "ce": 6.0146708488464355, "genuineness": 4.570107460021973, "identity": 0.5388275384902954, "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/emo_Distress/c80780146567765d1be8f9298c7fcc1bb3035b7e2768e4a3e6ae4fc9638b0999.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "c818a3c4ca25f921f781f8bd802eeb7f3870cef853932056f1e9859bb4d01cff", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ab303420f7c02533a092079575480ebee59499210ec622641d2019e56ccd870c", "generation_seconds_batch": 21.776515208999626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3619232177734375, "target_z": 2.3281250968479754, "ce": 5.77639102935791, "genuineness": 3.860914945602417, "identity": 0.4268585741519928, "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/emo_Distress/c818a3c4ca25f921f781f8bd802eeb7f3870cef853932056f1e9859bb4d01cff.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "c1f35c0e412df7edc77acff446e2c42a5fba564688e2c9a62fb4f65c72ad1362", "generation_seconds_batch": 15.379623943008482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25459349155426025, "target_z": -0.24999998176979288, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.626349151134491, "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/emo_Distress/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.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": "c86385aec42790a2e0f4e6682429efbbd1d4e2e31930c11469afece1bf99e61c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f0c8c4f7e338d4d49847d89a1d681aa0e4b0a40adac084cb6840bb56831c3dc6", "generation_seconds_batch": 16.001855536014773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.757845640182495, "target_z": 2.8124999498669303, "ce": 5.95112943649292, "genuineness": 3.660081624984741, "identity": 0.5177245140075684, "hypothesis": "Wrote the number on the envelope. Read it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "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/emo_Distress/c86385aec42790a2e0f4e6682429efbbd1d4e2e31930c11469afece1bf99e61c.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "a1c2e2239df3278c84d4914e74990984c37713816c225fb3fa72e4390c1add8b", "generation_seconds_batch": 18.029937613056973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16040223836898804, "target_z": -0.3652343606152272, "ce": 6.3641486167907715, "genuineness": 4.394378662109375, "identity": 0.5123857855796814, "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/emo_Distress/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "c957481e0709bd771de5ce02fe3e76e737976913fd486948809eb03c4d8ee699", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "760a2ce8dc50e91e5cf9b3571f9fc3dac8ff19dd7f3147106603a99e4ef83050", "generation_seconds_batch": 21.61119166004937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2226642370223999, "target_z": -0.28906250284846985, "ce": 6.0305562019348145, "genuineness": 4.720732688903809, "identity": 0.6216709017753601, "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/emo_Distress/c957481e0709bd771de5ce02fe3e76e737976913fd486948809eb03c4d8ee699.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "c998687c475be499376a7003952a5d324ff4f2f91830cf257eaf91af0819c8f3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "feb3da05ae188af4a2cd6ec80cdb189ce9bb0aa5cd336e258f6fb6b48db6cb36", "generation_seconds_batch": 23.10077690402977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4347453117370605, "target_z": 3.6406247550315918, "ce": 5.123106002807617, "genuineness": 3.528284788131714, "identity": -0.038175590336322784, "hypothesis": "Nee, de... De door staat nog open. Ik heb je het jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.21052631578947367, "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/emo_Distress/c998687c475be499376a7003952a5d324ff4f2f91830cf257eaf91af0819c8f3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "c9a2f2d6424a0aec83a008ed439b679326bbdbaea8e449c12d04ab5b28de8e1f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8e212644f7deda7e6f9019e018ba898328d56683b1033a45b2ddfd043883f665", "generation_seconds_batch": 21.058099809102714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.345343589782715, "target_z": 3.5312499293579473, "ce": 5.299830436706543, "genuineness": 3.886019229888916, "identity": 0.6257693767547607, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Timar, cours-tu prêt ?", "wer": 0.2222222222222222, "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/emo_Distress/c9a2f2d6424a0aec83a008ed439b679326bbdbaea8e449c12d04ab5b28de8e1f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "cafd0322439bef68a17d8ca304310474d0dfb3077fa5c6af83c2738bf47de97c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c4a467130a0b91a207df10ee6c398d4ca612c0594d2a6eedcdd8aaba3a26eb26", "generation_seconds_batch": 22.53241194493603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7207603454589844, "target_z": 0.32031250512724574, "ce": 5.895530700683594, "genuineness": 3.860914945602417, "identity": 0.49978578090667725, "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": 0.03999999999999915, "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/emo_Distress/cafd0322439bef68a17d8ca304310474d0dfb3077fa5c6af83c2738bf47de97c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "cb105bf5bf021fed357de299359d823cf3aa608c77be143aaf7008db13fca421", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ab72e13233ea4fa9504cb8f37a30f2f817ef6dad105ef33c749fa524a25d1105", "generation_seconds_batch": 21.601180746918544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11091190576553345, "target_z": -0.42578125370301084, "ce": 6.38797664642334, "genuineness": 4.469690799713135, "identity": 0.6811007261276245, "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/emo_Distress/cb105bf5bf021fed357de299359d823cf3aa608c77be143aaf7008db13fca421.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": "cb2bcb740d88476abe11a4b1548de9a37517dedeacc9d7c11faf7ea493dcd122", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b3b5ee9e023958e9bbcbd6c297ba6f1a0a2675aa8df8a989c3dd1a8d948ac9bd", "generation_seconds_batch": 23.407246778020635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7195305824279785, "target_z": 2.765624982909181, "ce": 5.526196479797363, "genuineness": 3.9425034523010254, "identity": 0.5084713697433472, "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": 0.03999999999999915, "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/emo_Distress/cb2bcb740d88476abe11a4b1548de9a37517dedeacc9d7c11faf7ea493dcd122.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "cb2bf33cb2fa9100d220e3e73f1acc4be1459b123d8b60cd9f3e93fc9e3a4460", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "244c8dc3d66c42bd79bf55566704f93ef57a2be0029426fd12cc499c0eb18106", "generation_seconds_batch": 22.12837370298803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1677696704864502, "target_z": 0.8671875085454096, "ce": 6.205295085906982, "genuineness": 4.68307638168335, "identity": 0.6014757752418518, "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/emo_Distress/cb2bf33cb2fa9100d220e3e73f1acc4be1459b123d8b60cd9f3e93fc9e3a4460.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "cb6542190136ffdfe6ff8942789132e265f759d66b156fca3e3d301c1a873d28", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d2a4337f8fd455859d1c1f4faa1ea788fd90615bdb638838f4fedcadeb8a5e1a", "generation_seconds_batch": 22.717480925959535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2380139827728271, "target_z": 0.9531249965818361, "ce": 5.959072113037109, "genuineness": 4.143336772918701, "identity": 0.537382960319519, "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/emo_Distress/cb6542190136ffdfe6ff8942789132e265f759d66b156fca3e3d301c1a873d28.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": "cc39cecd1313d6e32d2f07a0a29c5ed9b7aa0540cc3495d4e5747605377f0081", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Someone moved the little blue chair.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "09552f484980d5143f5b223b170ede059138b0a15bfeaccf4aedf22d080fb589", "generation_seconds_batch": 19.82278469100129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.295486569404602, "target_z": 1.0234374470184606, "ce": 5.974957466125488, "genuineness": 3.835810661315918, "identity": 0.5852176547050476, "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/emo_Distress/cc39cecd1313d6e32d2f07a0a29c5ed9b7aa0540cc3495d4e5747605377f0081.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": "ccb0bc977dc66c6d3b30a386cdc908dd17c295f3e6e3240c8646a5f8a500fc42", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fdb7a6045af8a185f7f8977670e506d2e09e6371709c02121c2fd1539d398076", "generation_seconds_batch": 18.288125770981424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0298590660095215, "target_z": 1.9218749943030602, "ce": 5.935244083404541, "genuineness": 4.093128204345703, "identity": 0.41218239068984985, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suche deine Schublade. Dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.19047619047619047, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/ccb0bc977dc66c6d3b30a386cdc908dd17c295f3e6e3240c8646a5f8a500fc42.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "ccc1658db332b8d8816a4a4ecffd6e65acc5c6d2c30984146b32af3c4c857339", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d7fb3f0f0a5b058d0b9111e9de9cc295d20654e130b11d91f01f286925472193", "generation_seconds_batch": 16.311393729993142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.315715789794922, "genuineness": 3.528284788131714, "identity": 0.6151804327964783, "hypothesis": "The door is still open. I put I put your coat on the chair Tell me when you are ready", "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/emo_Distress/ccc1658db332b8d8816a4a4ecffd6e65acc5c6d2c30984146b32af3c4c857339.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": "cccd8026c39d4e1199a9adbc5ac874499070a0c2b6019b3515b8df9efa27d4c3", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "84a42e623c548df786e5e60522f123e40d95ec01e1c7ead7320672716c205112", "generation_seconds_batch": 15.905154419015162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5496907234191895, "target_z": 3.7812499475881545, "ce": 5.184661865234375, "genuineness": 3.6789097785949707, "identity": 0.5764189958572388, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geht 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/emo_Distress/cccd8026c39d4e1199a9adbc5ac874499070a0c2b6019b3515b8df9efa27d4c3.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "cd098948520d9030f65f1841f88328bac6fb57512e96945ab6d6d4b7b85e0296", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "655d2c07b04d1e657752d91d6cd7bc188e5ae939b9cd59048e3aaf1d2befbed6", "generation_seconds_batch": 14.977032487047836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07898268103599548, "target_z": -0.46484373832127357, "ce": 6.300607204437256, "genuineness": 4.494794845581055, "identity": 0.7658751010894775, "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/emo_Distress/cd098948520d9030f65f1841f88328bac6fb57512e96945ab6d6d4b7b85e0296.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "cd8283dcd03182f5cea890e3c04cdc89c233911942696f9d42ccd743af7228df", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "80dd8d0389aa0ed3c3929ca2b6eef6f8dbff14658893bce58ab0340d04e85ad8", "generation_seconds_batch": 15.352947362000123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.400238275527954, "target_z": 2.3750000638057247, "ce": 5.998785495758057, "genuineness": 4.231201171875, "identity": 0.3742750287055969, "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/emo_Distress/cd8283dcd03182f5cea890e3c04cdc89c233911942696f9d42ccd743af7228df.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "cdecdee86f98b05abe91e82148aa67bcbf64bec70352f18a89b61166cc58f34f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3b057f50546f95723a52a6029d1357ebf39627eaac67965a232583e0282aa4eb", "generation_seconds_batch": 14.62552785500884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.566270112991333, "target_z": 2.5781248233948686, "ce": 5.708878040313721, "genuineness": 3.7291181087493896, "identity": 0.5578162670135498, "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/emo_Distress/cdecdee86f98b05abe91e82148aa67bcbf64bec70352f18a89b61166cc58f34f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "cdfb2a8a95e45c7fd4b79f2e482009f079111faf53c421e0d2148afb9e07dcfd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "af7b4ce8ba3e74f77cc32d38b06dea502e7e7dc27ed7013aad4ceada5282eda2", "generation_seconds_batch": 23.66067499399651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234206199645996, "target_z": 2.1718750125332673, "ce": 5.506340026855469, "genuineness": 3.948779582977295, "identity": 0.3114842176437378, "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/emo_Distress/cdfb2a8a95e45c7fd4b79f2e482009f079111faf53c421e0d2148afb9e07dcfd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "ce82a2e3f80a420b8c871932b1f9ccebe02ca49602b16ab0c5d069ed3d3b5915", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "40471ae117ed3f7fb5b95160e1344a5b6878a3f81682e9163b55fdd4a1951d39", "generation_seconds_batch": 20.663270646939054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2577863931655884, "target_z": -0.24609375883025658, "ce": 6.006728172302246, "genuineness": 4.406930446624756, "identity": 0.7575663328170776, "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/manual-comparison-v1/audio/emo_Distress/ce82a2e3f80a420b8c871932b1f9ccebe02ca49602b16ab0c5d069ed3d3b5915.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "cec5474e822073b9e09aa9464fe7eca7d465ba84d13f78bf695b029ec606f61c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1b1011a44286ecf24eea1091b39d3998488d7c80ab84a648f8f35a3a80a31bde", "generation_seconds_batch": 22.161250276956707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8388985395431519, "target_z": 0.4648437747816878, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.7776790857315063, "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/emo_Distress/cec5474e822073b9e09aa9464fe7eca7d465ba84d13f78bf695b029ec606f61c.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": "cec829cd95e9fbb1736798afb37202dd032b4dd45094d434ca7ce5ebb77426f1", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdedbd20e6953c045b1dc901f483757b96fcc6d9b1c4bf8b3de162175522e139", "generation_seconds_batch": 17.347064743051305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.37469482421875, "target_z": 2.3437499886061204, "ce": 6.133810997009277, "genuineness": 4.15588903427124, "identity": 0.7310723662376404, "hypothesis": "Plus a déplacé la petite chaise 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/emo_Distress/cec829cd95e9fbb1736798afb37202dd032b4dd45094d434ca7ce5ebb77426f1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "cf25b45c0282392cfc757d9f92f454538ce0d0f62e934ad47a3159acb0cb2c9c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a4ef33bee4cf6dd0452910243d149ceb1f6ef7741106a31046a8e64052a97f7b", "generation_seconds_batch": 22.36436681204941, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6281655430793762, "target_z": 0.20703123775157958, "ce": 5.998785495758057, "genuineness": 3.848362922668457, "identity": 0.47688937187194824, "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/emo_Distress/cf25b45c0282392cfc757d9f92f454538ce0d0f62e934ad47a3159acb0cb2c9c.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "76b055abc50973678d26297686d171ea97763243577c4ec22471f0e4245c5bdf", "generation_seconds_batch": 16.47733486199286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14124467968940735, "target_z": -0.38867188055451624, "ce": 6.4515180587768555, "genuineness": 4.65797233581543, "identity": 0.594816267490387, "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/emo_Distress/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "cf740283ffa90f3f6a1466e105b67aaacc4c519aff06753ae375072ac8698bdf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a69a048beadd96cf67f7f7ed63dff8a9502edc730556c902c278aff2cd4f7d78", "generation_seconds_batch": 24.38180191302672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2188564538955688, "target_z": 0.9296875131029614, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.47330883145332336, "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/emo_Distress/cf740283ffa90f3f6a1466e105b67aaacc4c519aff06753ae375072ac8698bdf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "cf9edecccc50c95d4a850275c583395836b1b5cee199f87b8a5efafa9eadc2be", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "92badf011aade6d4395119e27bc7db8c9b43d539509db6b036f734e6872e1a42", "generation_seconds_batch": 23.41574717895128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3623546361923218, "target_z": -0.11816408251050078, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.4147535562515259, "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/emo_Distress/cf9edecccc50c95d4a850275c583395836b1b5cee199f87b8a5efafa9eadc2be.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "cfefd748352952e76c852d9e4eaa4d41a426a7c3560a7aa1a9328c9fe7eb299f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "14680198d3036d988623671c3dd65ce542af06b775256cd83ade608bc0062f4c", "generation_seconds_batch": 23.090371670899913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.204854965209961, "target_z": 3.3593749532850943, "ce": 5.411027908325195, "genuineness": 3.9048471450805664, "identity": 0.5838222503662109, "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/emo_Distress/cfefd748352952e76c852d9e4eaa4d41a426a7c3560a7aa1a9328c9fe7eb299f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "d01285b4b649af157e6bf115450d602335f8c0d7148e4237eaacd4b746d89d51", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3b1320f1b0d15a30df05ab10e6fdc30e79e2444f517bdb82fec6581ef3107bd4", "generation_seconds_batch": 23.090371670899913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4602887630462646, "target_z": 3.671874830231196, "ce": 5.246217727661133, "genuineness": 3.961331605911255, "identity": 0.5654047727584839, "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/emo_Distress/d01285b4b649af157e6bf115450d602335f8c0d7148e4237eaacd4b746d89d51.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "d111d9de3f944087ab5e6ace4cf57a1cd598987e455e99ee935c7d30e3da44aa", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "535cc5ef8fddcbc9e55bbd6690f0f59f12591790eeff724a63b20abeb9dc8bcd", "generation_seconds_batch": 20.402935312944464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.068174123764038, "target_z": 1.96874996126081, "ce": 6.141753673553467, "genuineness": 4.105680465698242, "identity": 0.5033246278762817, "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/emo_Distress/d111d9de3f944087ab5e6ace4cf57a1cd598987e455e99ee935c7d30e3da44aa.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "f53c6ba780573f3d5971c5e75e44fd8b705e880e415085ab39a81e4ac9fac237", "generation_seconds_batch": 17.09706343698781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.292664527893066, "genuineness": 3.7918784618377686, "identity": 0.3969789147377014, "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/emo_Distress/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "d1250d8393d306cdfccc32fb1f9772d1ee157c1f6393ab547aeed037ce0390b7", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9da91956a8423e68541233ac64829ee25578c21005cbe6a7bd22113f8a9e813f", "generation_seconds_batch": 16.59805244009476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2418217808008194, "target_z": -0.2656250011393879, "ce": 6.09409761428833, "genuineness": 4.137060642242432, "identity": 0.31946438550949097, "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/emo_Distress/d1250d8393d306cdfccc32fb1f9772d1ee157c1f6393ab547aeed037ce0390b7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "d19dc5ff131bb72fb71b902a57c8c5922bf2a4a3e550f8ebd63a10fda3116cdc", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "676338a8cfd7a046c474225cd142692cf516b854232a8823be3aa492324c6aad", "generation_seconds_batch": 20.715315215988085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3274158239364624, "target_z": 1.0624999680971376, "ce": 5.927301406860352, "genuineness": 4.293961524963379, "identity": 0.5631595253944397, "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/emo_Distress/d19dc5ff131bb72fb71b902a57c8c5922bf2a4a3e550f8ebd63a10fda3116cdc.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "d1b4e423d28615deade103010a288e524148d869d7a2370c8b9cbb0b50d10cbf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "893ec828608ab0de8a81e97fecbda20c1a84545720a01cbfb7abf7c352fa8fdb", "generation_seconds_batch": 21.896303591900505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09814020991325378, "target_z": -0.44140625484239876, "ce": 5.7128496170043945, "genuineness": 4.319066047668457, "identity": 0.7996125817298889, "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/emo_Distress/d1b4e423d28615deade103010a288e524148d869d7a2370c8b9cbb0b50d10cbf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "d1cb787262a058409c72542d762b6f5e0806dc8a1ca6f9670b16ce807326d231", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "53699406077fe284a971a77256f5c7a305cfcc66845b05c7ec36e12e4fed5b7f", "generation_seconds_batch": 17.413138875039294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2418217808008194, "target_z": -0.2656250011393879, "ce": 6.356205940246582, "genuineness": 4.469690799713135, "identity": 0.5304341912269592, "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/emo_Distress/d1cb787262a058409c72542d762b6f5e0806dc8a1ca6f9670b16ce807326d231.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "d1d8bb9c744879c22277aa7f7cd1578674e9bd07150bbd821039c06f81a27030", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a596ecd7d91f1c7dedc608f756ad61773222e3b697bddb41d55ac57ce2252955", "generation_seconds_batch": 18.408764499938115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6914092302322388, "target_z": 1.5078125917207295, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.6704187393188477, "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/emo_Distress/d1d8bb9c744879c22277aa7f7cd1578674e9bd07150bbd821039c06f81a27030.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "d2237805823542907067811f4e55bbbb3df729dacfdbb00ab4871c07ad870496", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c84fd33e62fab739d880f4fbd185b24dcccc167dd7caa8dc6a7fc59cf536d8a3", "generation_seconds_batch": 21.670634682988748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17636683583259583, "target_z": -0.34570313653630297, "ce": 6.229123115539551, "genuineness": 4.7332844734191895, "identity": 0.6069678068161011, "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/emo_Distress/d2237805823542907067811f4e55bbbb3df729dacfdbb00ab4871c07ad870496.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "57260ca6ce709c5c344fcbe561fb80198b254b844633d38f6e4895e061d30a5c", "generation_seconds_batch": 17.567081885994412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15241992473602295, "target_z": -0.37499999088489644, "ce": 6.23706579208374, "genuineness": 4.344170093536377, "identity": 0.6301380395889282, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana, y llévatelas cuando te vayas.", "wer": 0.043478260869565216, "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/emo_Distress/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "d2476ac7f414ad5043748b05f81277bcd1f625ebfd1ce69da45251c782a1439e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ffb9c9fdf431f2b6f5ae8883c7d9e661e682b6790edda25e522f92c54268268a", "generation_seconds_batch": 16.63374863297213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08536851406097412, "target_z": -0.45703125598178673, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.6451226472854614, "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/emo_Distress/d2476ac7f414ad5043748b05f81277bcd1f625ebfd1ce69da45251c782a1439e.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": "d271c26eec14652c4cab9037b2851210914b8eaa48da30bcc864dbabe68895e5", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14f8a7509ac503e323bf63434d2d5dfe35fab4383c3e90c223e1b0cea275596b", "generation_seconds_batch": 21.636190418037586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9621927738189697, "target_z": 3.0624999680971374, "ce": 5.696964263916016, "genuineness": 3.7542223930358887, "identity": 0.4911065697669983, "hypothesis": "La carretera girá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado me tomar y son por el chas de Kimao. Askí te esperaré al otro lado.", "wer": 0.7619047619047619, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/d271c26eec14652c4cab9037b2851210914b8eaa48da30bcc864dbabe68895e5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "d28ceb695e43375d791be4060c6f21b6a2eae0d552104491060208cdcc1e2eab", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "aa7aec5aec342bdd95461d7998b85b5400a02d9afa3ddfeafb636af911461d7c", "generation_seconds_batch": 21.143690889002755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1537680625915527, "target_z": 3.2968748028858856, "ce": 5.6413655281066895, "genuineness": 4.042920112609863, "identity": 0.1230209469795227, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen samen kijken.", "wer": 0.2222222222222222, "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/emo_Distress/d28ceb695e43375d791be4060c6f21b6a2eae0d552104491060208cdcc1e2eab.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "d32e97962677b8291608b814049e052ea940f61f4030ebe73ec6a33505d24b10", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6ce78bdc70b08deb8e6d4f405288dc97270f0256ac3cad9b2409a73214d3734f", "generation_seconds_batch": 21.1292721190257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9085279703140259, "target_z": 1.773437501709082, "ce": 5.903473377227783, "genuineness": 3.8169827461242676, "identity": 0.5242283940315247, "hypothesis": "I found the little box. It's beside the old Winte. We can look inside together.", "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/emo_Distress/d32e97962677b8291608b814049e052ea940f61f4030ebe73ec6a33505d24b10.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "d3a10e207d1865773d2dd1f86c1587a2535d0aae0bdb586d2bcee55e36d4e449", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9b815b21bf6a887f527da4f6817058af83ba610d76be7a9df32ce70591613f7c", "generation_seconds_batch": 21.058099809102714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.557967185974121, "genuineness": 3.6663577556610107, "identity": 0.6033750772476196, "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/emo_Distress/d3a10e207d1865773d2dd1f86c1587a2535d0aae0bdb586d2bcee55e36d4e449.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": "d3e2f1e0a5444c225b9df164644915ba5caf4b721582b7d3ab83195a62f31ddc", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "185fd62ef72df63c6a456de00a5cdbb72d50241235c5a46031376fb0bca5fa66", "generation_seconds_batch": 17.16468862001784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 6.133810997009277, "genuineness": 3.923675537109375, "identity": 0.15578696131706238, "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/emo_Distress/d3e2f1e0a5444c225b9df164644915ba5caf4b721582b7d3ab83195a62f31ddc.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "96b0af6e2785556cd1f1765cfdcd350d6b9a640ccccbc2aebccc8e3709d16b1b", "generation_seconds_batch": 15.539491947973147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04705342650413513, "target_z": -0.5039062593999506, "ce": 6.006728172302246, "genuineness": 4.432034492492676, "identity": 0.6995097398757935, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un", "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/emo_Distress/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "d470191df19662d18486ed6f7c1031cee157dfcac67f9b4e832c21086d6780ca", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "23f11b31f8b6bd5053cd5bc42ff3b32533a02848e763a3c67c6d9851a9ef8271", "generation_seconds_batch": 21.207203656085767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31206610798835754, "target_z": -0.17968749487275426, "ce": 5.974957466125488, "genuineness": 4.068024158477783, "identity": 0.4004130959510803, "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/emo_Distress/d470191df19662d18486ed6f7c1031cee157dfcac67f9b4e832c21086d6780ca.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "d492696f7efe232a4db037b642dd81966203e0c35536e0094de01ea78f7371ad", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "633f9a4cb8fd82c127eb27ce9b9cd87aa9c5902824791a4757d8d8e532359bf1", "generation_seconds_batch": 21.853147260961123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 5.808161735534668, "genuineness": 3.9801597595214844, "identity": 0.4290062189102173, "hypothesis": "He encontrado a la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/d492696f7efe232a4db037b642dd81966203e0c35536e0094de01ea78f7371ad.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "d53f725f5bc613386756f40c2c70a027abe7f722a9dc6ede94da7925f32d9120", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "8bf75ab4141a0d47835336aaf805b3adc5b283b97d8868f7cd5db492d614305e", "generation_seconds_batch": 20.67907530395314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.447517156600952, "target_z": 3.656249938473051, "ce": 5.550024509429932, "genuineness": 3.292933464050293, "identity": 0.5306793451309204, "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": 0.03999999999999915, "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/emo_Distress/d53f725f5bc613386756f40c2c70a027abe7f722a9dc6ede94da7925f32d9120.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": "d6d2217c77bb86137d8b11b807a68c41832ed3fbde51264c4f1ba3f7e35f9a08", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Escribí el número en el sobre.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9b2887d654a43ebfcfdafd619667176af98279d869c9b1639d481a29b207fc1", "generation_seconds_batch": 16.09638563496992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.72849440574646, "target_z": 3.9999998906187573, "ce": 5.700935363769531, "genuineness": 3.9173994064331055, "identity": 0.40768831968307495, "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/emo_Distress/d6d2217c77bb86137d8b11b807a68c41832ed3fbde51264c4f1ba3f7e35f9a08.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "d7902f22a18bc87c0b995430bf75fa579c751a2ab5338b78549e2b3e419ac037", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "64dcffe8d562129bc7803caf264fa4cae57b9a7a0350bc89dbcd0886df4a378f", "generation_seconds_batch": 23.112864642986096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451324939727783, "target_z": 2.43749992252162, "ce": 5.863759994506836, "genuineness": 4.482243061065674, "identity": 0.4747055768966675, "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/emo_Distress/d7902f22a18bc87c0b995430bf75fa579c751a2ab5338b78549e2b3e419ac037.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "d82dc7d346861e9dd06fc1c2e6899380e65c4d8ca45c51119c4e4b208e10ad0b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3d0686b2493579a6714e514849f92a30483a93ece5e1618ef1beeba32ea7d3a1", "generation_seconds_batch": 21.292625873931684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23543593287467957, "target_z": -0.27343750170908193, "ce": 5.95112943649292, "genuineness": 4.557555198669434, "identity": 0.5277761816978455, "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/emo_Distress/d82dc7d346861e9dd06fc1c2e6899380e65c4d8ca45c51119c4e4b208e10ad0b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "d8609411cb5b8899e95ac73d89b873662888eb84a147a2a5d8ad8100cb0d99a0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "80065da16be00b6851bc9498c50e63d0d281d20afabb3e7b4cccd0a3c647fd51", "generation_seconds_batch": 15.63424456503708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21947132050991058, "target_z": -0.29296874401821327, "ce": 6.141753673553467, "genuineness": 4.18099308013916, "identity": 0.38292396068573, "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": 0.03999999999999915, "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/emo_Distress/d8609411cb5b8899e95ac73d89b873662888eb84a147a2a5d8ad8100cb0d99a0.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": "d88b1e0334345931e8bdbad3b48165e5d822f2b6e6922762fd05bbfe12cdcfd6", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fd826bd2e13f42b7892d006df4cc3b24f8b7e8f52a195cb0071e9b58629dc54", "generation_seconds_batch": 15.798881446942687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.808932304382324, "target_z": 2.8749998085828254, "ce": 5.629451274871826, "genuineness": 4.193545341491699, "identity": 0.45420587062835693, "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/emo_Distress/d88b1e0334345931e8bdbad3b48165e5d822f2b6e6922762fd05bbfe12cdcfd6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "d88c39bf4b41fda5db8bad8741dcbf6b5dbc77a1b11f13fa04ee86a4509822ed", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1d1ff79a4be85f876215a98716a22df51019af3df46c4f519b40d189bdae0a6b", "generation_seconds_batch": 24.51027756300755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.068789005279541, "target_z": 0.7460937223698423, "ce": 5.569881439208984, "genuineness": 3.7291181087493896, "identity": 0.43877148628234863, "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/emo_Distress/d88c39bf4b41fda5db8bad8741dcbf6b5dbc77a1b11f13fa04ee86a4509822ed.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "d8ef27d0b7dc7faf4f551d453a02f5df20be9aa8fa4c8ac79b18a43d7aa1766f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "335e7e3328cc0a4cc8d1b906d192d4510d14c6400f84838d563a8411193b2642", "generation_seconds_batch": 14.432247332064435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 5.9431867599487305, "genuineness": 4.20609712600708, "identity": 0.5493710041046143, "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/emo_Distress/d8ef27d0b7dc7faf4f551d453a02f5df20be9aa8fa4c8ac79b18a43d7aa1766f.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": "d93daf52ac3475b636e0afa731112fdd411c83b2c820100d44dba5f1b569a4a7", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6552c217cb3cb54c0e9a5184562070e3efe3b4a7df67f70e1758ab0bb0370be", "generation_seconds_batch": 16.113896563998424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.400238275527954, "target_z": 2.3750000638057247, "ce": 5.657250881195068, "genuineness": 3.936227321624756, "identity": 0.7116000652313232, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Il était ici, près de la g près de la grande bibliothèque. Une volette un métron après le déjeuner.", "wer": 0.42857142857142855, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/d93daf52ac3475b636e0afa731112fdd411c83b2c820100d44dba5f1b569a4a7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "d97a3a505a2d822773f0e729e70ae861c01982b5c13faf5768a5a0ebb7b4a827", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a3eaf939048378122d5904c62653a638e7039fdef831fccb280f156440af804d", "generation_seconds_batch": 21.81522840098478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19073501229286194, "target_z": -0.32812498746673263, "ce": 5.95112943649292, "genuineness": 4.457139015197754, "identity": 0.4734046757221222, "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/emo_Distress/d97a3a505a2d822773f0e729e70ae861c01982b5c13faf5768a5a0ebb7b4a827.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "d9d3a3570759b652fc4c284b8980cd9db03c9cfcd67492afcf78d2e709507796", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4614d1be1ec1f9da2597d9b57ad4789f26da9bdb8f066b0fd484644174400815", "generation_seconds_batch": 17.141835490008816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8318978548049927, "target_z": 1.6796875677935827, "ce": 6.133810997009277, "genuineness": 4.356721878051758, "identity": 0.6632368564605713, "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/emo_Distress/d9d3a3570759b652fc4c284b8980cd9db03c9cfcd67492afcf78d2e709507796.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "da7b43de7725b11462aaab44873cc401033e735cb49d872abe15022869d0b671", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "151254e15874e60dbcfa30a6c513b244892189797aeec56d7409b6ae5c462300", "generation_seconds_batch": 17.136157016037032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.268836498260498, "genuineness": 4.7081804275512695, "identity": 0.5578572154045105, "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/emo_Distress/da7b43de7725b11462aaab44873cc401033e735cb49d872abe15022869d0b671.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": "da7fbaee2d38394372f241d5ceba1618571ab4fb18528e205a8b39f7a9ee02e7", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c3944cc72e3c528f1364615fc43042ee2605c1130e503cdd02fc481e86574bc", "generation_seconds_batch": 15.746242263005115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8600192070007324, "target_z": 2.937499958982034, "ce": 5.95112943649292, "genuineness": 3.8546390533447266, "identity": 0.08620511740446091, "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/emo_Distress/da7fbaee2d38394372f241d5ceba1618571ab4fb18528e205a8b39f7a9ee02e7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "da865dd06f367720f9d0cc18fbcbd449d76d27c91acaba1b227e337ce0069065", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bdb7f95b297d07c83ed4028acbfb5a8c0b55595a0ba6893b4b328e71820d2eb3", "generation_seconds_batch": 16.416928112041205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5279550552368164, "target_z": 2.531249856437119, "ce": 6.0146708488464355, "genuineness": 4.287685871124268, "identity": 0.7352717518806458, "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/manual-comparison-v1/audio/emo_Distress/da865dd06f367720f9d0cc18fbcbd449d76d27c91acaba1b227e337ce0069065.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": "daaa7e376aea6fb2b95bdab747d1a12d886c6ee1ecbf03eac9b4f2f7e622364a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6c635e4cdfb358c6fac80aa8277efe66293fee93ccaf53790f6db48adb8d2478", "generation_seconds_batch": 15.967072019004263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3593450784683228, "target_z": 1.1015624891758145, "ce": 6.109982967376709, "genuineness": 3.9048471450805664, "identity": 0.2749135196208954, "hypothesis": "Ik schreef het nummer op. Hat even lopen. Lees het goed. Controleer de laatste twee cijfers. Bel me, wanneer je even tijd hebt.", "wer": 0.17391304347826086, "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/emo_Distress/daaa7e376aea6fb2b95bdab747d1a12d886c6ee1ecbf03eac9b4f2f7e622364a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "dace7614b7c4a5178e6ad7abc02e19791e0cc3689809177815e836ee248f0ab3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "26f9b2d3d1ac229b0b5c239ad3289e7cbf2647a694f466c373e7edcada769e15", "generation_seconds_batch": 20.29927638405934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.447517156600952, "target_z": 3.656249938473051, "ce": 5.506340026855469, "genuineness": 3.7040140628814697, "identity": 0.10367575287818909, "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/emo_Distress/dace7614b7c4a5178e6ad7abc02e19791e0cc3689809177815e836ee248f0ab3.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": "dae25913b87d0f0306ded98c49cf69253e2ff5aaf2373f9a6a0725f6392b1f52", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I wrote the number on the envelope.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b147eee698ce3894d199523cbb21d5a54f91a49ad10f25c39b1b4b3bf5c621d8", "generation_seconds_batch": 22.77610422403086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9366493225097656, "target_z": 3.031249892897533, "ce": 5.8875885009765625, "genuineness": 3.2238969802856445, "identity": 0.31624042987823486, "hypothesis": "I wrote the number on the envelope. Read it carefully and check the last t two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "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/emo_Distress/dae25913b87d0f0306ded98c49cf69253e2ff5aaf2373f9a6a0725f6392b1f52.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "daf47724f2c8b03634ef51835e6e2bd8343f2408541647a13c396e621c90b1e5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6b981798f887e8fab51da89dc7171c40c7d922524572e28baeccf6edad7b2557", "generation_seconds_batch": 14.275523404008709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5595176815986633, "target_z": 0.12304686118492117, "ce": 6.165581703186035, "genuineness": 4.15588903427124, "identity": 0.4322636127471924, "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/emo_Distress/daf47724f2c8b03634ef51835e6e2bd8343f2408541647a13c396e621c90b1e5.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8ab60f3029db63fbee42661d4fa14fceb959f03b5d4e657ab9398ea5f13cc392", "generation_seconds_batch": 14.356919717043638, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30089086294174194, "target_z": -0.19335938454237403, "ce": 6.308549880981445, "genuineness": 4.168440818786621, "identity": 0.4105326533317566, "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": 0.03999999999999915, "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/emo_Distress/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "db2018b076f0215a7cdab5a0e91941a2c0d72e26b7b52f73e9b40eb6e1854dae", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c190f58c1786e33cd94108ca032b340a8ff58c3f6061d4c8c2fdd6cb12dc3286", "generation_seconds_batch": 20.749186484958045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5124220848083496, "target_z": 0.06542970822261825, "ce": 6.022613525390625, "genuineness": 4.595211505889893, "identity": 0.6600626707077026, "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/emo_Distress/db2018b076f0215a7cdab5a0e91941a2c0d72e26b7b52f73e9b40eb6e1854dae.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": "db2c46833b4133ef51bc49d30e33e38e4dbf7b13055e0ff3a7ecddc8f8a9f13c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "92fa7b7527af208693a6e431f38d85d6b408a8bfd8b7839c87ecb596c8f81f86", "generation_seconds_batch": 15.967072019004263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.808932304382324, "target_z": 2.8749998085828254, "ce": 5.967014789581299, "genuineness": 3.747946262359619, "identity": 0.3219064176082611, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed. Controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "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/emo_Distress/db2c46833b4133ef51bc49d30e33e38e4dbf7b13055e0ff3a7ecddc8f8a9f13c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "db80b4c34ffabd96381d8c1090581bf910eddc309c964003a7393ca55fbcf292", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2ac5ac64a14319795fdd729fbf0963d064ca28004f39303f61518e9717eaac90", "generation_seconds_batch": 22.551244683098048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9532289505004883, "target_z": 1.8281250603875612, "ce": 6.022613525390625, "genuineness": 3.898571252822876, "identity": 0.4890589714050293, "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/emo_Distress/db80b4c34ffabd96381d8c1090581bf910eddc309c964003a7393ca55fbcf292.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "dbb0f67c96c1b907b13c84a2f05d944592b7f4ba10e6ab6769aef771b66034e1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3ff7838f8f4c7cf96f1a5a101d44818f957bf2dcf6726d880ee549a063878144", "generation_seconds_batch": 22.12837370298803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8005834221839905, "target_z": 0.4179687349031097, "ce": 6.086154937744141, "genuineness": 4.632867813110352, "identity": 0.5845692157745361, "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/emo_Distress/dbb0f67c96c1b907b13c84a2f05d944592b7f4ba10e6ab6769aef771b66034e1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "dbe5a0c76ceebd3ef98892784293ae5529af49191d3488e7070c2af923d72c6b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "405ab87d2e41e1559dcc9d02f5ce17b8721cea4d143955217dc27c846c21ae96", "generation_seconds_batch": 21.48097402602434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1958911418914795, "target_z": 2.1250000455755176, "ce": 5.839932441711426, "genuineness": 4.174716949462891, "identity": 0.34304356575012207, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. Zeg maar wanneer je klaar bent.", "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/emo_Distress/dbe5a0c76ceebd3ef98892784293ae5529af49191d3488e7070c2af923d72c6b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "dc144595ea23f7b0a3445fd2af8c0e0208a7a2ea3d556abc4eef230a0ddafef4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "af369f8562c9626766ea9ed3d254c02c188a917688dec9a43ea09418657e6e8a", "generation_seconds_batch": 20.553937393939123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1448042392730713, "target_z": 2.062499895176309, "ce": 6.324435234069824, "genuineness": 3.9801597595214844, "identity": 0.2548280358314514, "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/emo_Distress/dc144595ea23f7b0a3445fd2af8c0e0208a7a2ea3d556abc4eef230a0ddafef4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "dd8712c0aa28ed8c15f6a249263acf5380901b9781e14b4ad29b737de8ee7222", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "04ba340230acac141dbd8ee78b3fda1b8d2ee68f49b8e7bcbb67ec9c25ea4b7c", "generation_seconds_batch": 21.818212548969314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5126054286956787, "target_z": 1.28906250284847, "ce": 6.109982967376709, "genuineness": 4.13078498840332, "identity": 0.503646731376648, "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/emo_Distress/dd8712c0aa28ed8c15f6a249263acf5380901b9781e14b4ad29b737de8ee7222.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "dd9bf3cf4afe06203dc63f2477cc6c4a1be7af7237c838560c1ccd0c701894b8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6502a49041222705617048dad61100b0c60ce1720729883b4d43dcd4fc66b840", "generation_seconds_batch": 22.521469488972798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1204906702041626, "target_z": -0.4140625119635734, "ce": 6.284721851348877, "genuineness": 4.231201171875, "identity": 0.8035861253738403, "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/emo_Distress/dd9bf3cf4afe06203dc63f2477cc6c4a1be7af7237c838560c1ccd0c701894b8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "ddea434d86b2b345cc9a279a06bf553f674808fb452cb1e8ef637ad24a7d4a22", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d74b5d61c016b71245dee90e6d60eb7e877110c5c9eb7fb705bf19a29c2d0418", "generation_seconds_batch": 22.000364835956134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8855626583099365, "target_z": 2.9687500341816384, "ce": 5.510311126708984, "genuineness": 3.998987913131714, "identity": 0.5274155735969543, "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/emo_Distress/ddea434d86b2b345cc9a279a06bf553f674808fb452cb1e8ef637ad24a7d4a22.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "ddf7dc028591aa1cd42deaf254e335ac4fdfa1776c80bad6850d5ee28e5683a5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "440132e0e3ac3829d3c4d4e1dded6ae55a90848901ce9a7f96bdd0778052859c", "generation_seconds_batch": 24.117108173086308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09175437688827515, "target_z": -0.4492187371818856, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.6977096199989319, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/ddf7dc028591aa1cd42deaf254e335ac4fdfa1776c80bad6850d5ee28e5683a5.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": "dea3609b044a303fdb3357c818aaee6df69ec934053a75e2f5e9aadbc1478a5d", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19862ccfbd43e075629652d3ebf8cf34f64045873b254a7f59ed90f9527b57e0", "generation_seconds_batch": 19.130469389958307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.065596103668213, "target_z": 0.742187499430306, "ce": 5.982900142669678, "genuineness": 4.080576419830322, "identity": 0.26895672082901, "hypothesis": "Niemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge poekenkast. We zetten het maar de lunch terug.", "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/emo_Distress/dea3609b044a303fdb3357c818aaee6df69ec934053a75e2f5e9aadbc1478a5d.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": "deb6e5d58c746a48829778a5fecaad25d1649805941560c769cf50967cb382bb", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9db6a51b2566897438cf27d58b493c1f4fbd72b629a1c06aef7f8985ea2d12cb", "generation_seconds_batch": 15.300253112916835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.851055383682251, "target_z": 1.7031250512724576, "ce": 5.784333229064941, "genuineness": 4.20609712600708, "identity": 0.7642381191253662, "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/emo_Distress/deb6e5d58c746a48829778a5fecaad25d1649805941560c769cf50967cb382bb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "dff072b520845eff64375f2cc1a10d050aeb23cf89710eba2b7d09268330b536", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ff960e3950381828586d94a272e671fa97fffe2010a1624e6144e6aab559b262", "generation_seconds_batch": 22.71864444797393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9787722826004028, "target_z": 1.8593749897455085, "ce": 5.6532793045043945, "genuineness": 4.532451152801514, "identity": 0.7801086902618408, "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/emo_Distress/dff072b520845eff64375f2cc1a10d050aeb23cf89710eba2b7d09268330b536.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "e033126ab9f105c624e15d195631fe1dc52e30fb605b9f1ca97bb4031be07851", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "cbbce522d3e7b1ae90d759a385822d033f26094018bdedfc769b420bb305dd20", "generation_seconds_batch": 16.0166466179071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 5.9431867599487305, "genuineness": 4.024092197418213, "identity": 0.5385841727256775, "hypothesis": "The door is still open. I put your coat on a chair. Tell me when you are ready.", "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/emo_Distress/e033126ab9f105c624e15d195631fe1dc52e30fb605b9f1ca97bb4031be07851.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "e0a899b83aefe23d4266bd4dc9ebaeddfacaffc1c5ffc119611140e6ddacb400", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "15c79abef306041c068395bcdd2472db78fa4ef80107c70d192fa6cbc756465d", "generation_seconds_batch": 16.200483538093977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.183119297027588, "target_z": 2.1093748621340587, "ce": 6.0146708488464355, "genuineness": 4.2374773025512695, "identity": 0.5526062250137329, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen 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/emo_Distress/e0a899b83aefe23d4266bd4dc9ebaeddfacaffc1c5ffc119611140e6ddacb400.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "e0cac9e210770b703a038b97d38e7e2e690c118c5be6d74683240ad553deeecd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "0dfe7ef112d01447dd5119c96746c678e1d3808ea43c1542a4991a084e94d57d", "generation_seconds_batch": 20.130076940986328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16838452219963074, "target_z": -0.35546876680597217, "ce": 5.919358730316162, "genuineness": 4.68307638168335, "identity": 0.7406246662139893, "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/emo_Distress/e0cac9e210770b703a038b97d38e7e2e690c118c5be6d74683240ad553deeecd.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": "e0f16264851b51e4abf369db9b35751c68cb211b66df72e2f23fe59263636826", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The keys are on the kitchen table.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "59f82ab7276a5045e6389de19b6b879eeb4279b8dd059a78545fd5b3f80e8d36", "generation_seconds_batch": 22.19628257700242, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0515944957733154, "target_z": 3.171874793770782, "ce": 5.7406487464904785, "genuineness": 3.7165660858154297, "identity": 0.5554736852645874, "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/emo_Distress/e0f16264851b51e4abf369db9b35751c68cb211b66df72e2f23fe59263636826.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "e0f975f590297fc4ba4e4c5cae24109bf10bb2b199dc3cba36c97e01d12833a9", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4fe6784b15307bc720580b702c09e1e6960b70ed4cc8b96a28554c350cd8418d", "generation_seconds_batch": 17.32784017897211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34479355812072754, "target_z": -0.13964845451960742, "ce": 6.205295085906982, "genuineness": 4.971774101257324, "identity": 0.7216890454292297, "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/emo_Distress/e0f975f590297fc4ba4e4c5cae24109bf10bb2b199dc3cba36c97e01d12833a9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "e171b1d77d648540b654536ebf70ccca2db309ebfb62ba80d199ecc0de943c95", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3cbd4ee842f36c8615f855b572aa8fa44aedfac96cec27c9087d3064a4d040ef", "generation_seconds_batch": 20.103449468966573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 5.681078910827637, "genuineness": 3.9173994064331055, "identity": 0.4289517402648926, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. Het oude raam. We kunnen daar samen in kijken.", "wer": 0.2222222222222222, "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/emo_Distress/e171b1d77d648540b654536ebf70ccca2db309ebfb62ba80d199ecc0de943c95.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e1c574d30d9c2e9c36236f532cd471f36701ae6a9ad5eeea4e3c119f3ab72b38", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9f4ae1cae191c13afbf6dcb297fcd5dae48c77718d8f15fe7c8d7c6be018bb6d", "generation_seconds_batch": 15.101821673102677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7463037371635437, "target_z": 0.35156250740602163, "ce": 5.911416053771973, "genuineness": 3.9676074981689453, "identity": 0.7637607455253601, "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/emo_Distress/e1c574d30d9c2e9c36236f532cd471f36701ae6a9ad5eeea4e3c119f3ab72b38.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e21faa8f5427632728eca638382577adb66741f6cb0637cbb486335c91cad605", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "c566ba69d7e8fc89d16756fb2fa79f395f7dfdbcf5775fc93a71d9c2be7f57e1", "generation_seconds_batch": 22.521469488972798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 6.252951145172119, "genuineness": 4.287685871124268, "identity": 0.5527864694595337, "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/emo_Distress/e21faa8f5427632728eca638382577adb66741f6cb0637cbb486335c91cad605.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e228764fb4643252189415a4ecc98a32cdd2689df672e5789f7a25d7dab99534", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "57d82aa73c62ea5004d8aa111dee58673f31079782876d28826737d395807d18", "generation_seconds_batch": 21.661893568001688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5068344473838806, "target_z": 0.05859374515760123, "ce": 6.316492557525635, "genuineness": 4.193545341491699, "identity": 0.340284138917923, "hypothesis": "I found the little Bacchus. 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/emo_Distress/e228764fb4643252189415a4ecc98a32cdd2689df672e5789f7a25d7dab99534.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "e269624112228110adda2383e971ef97066a9c50dcd2f0e76608603e83b4595b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "adb38c9827d89d5a73aaad749dc5b2fcbe50c4cca3456cbacf7b772d21659d3d", "generation_seconds_batch": 23.732408197945915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.230646550655365, "target_z": -0.2792968725788006, "ce": 5.982900142669678, "genuineness": 4.3127899169921875, "identity": 0.6633588075637817, "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/emo_Distress/e269624112228110adda2383e971ef97066a9c50dcd2f0e76608603e83b4595b.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": "e2cca7fc776cd9d695b718e293a0699c87674d066e5934b7f3430cea148ccab4", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "07f3e3678ac9f57ceb17cc4abf77477b00e3e64d4a06ad1450107667e6363786", "generation_seconds_batch": 20.37998330593109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6939871311187744, "target_z": 2.7343749077095763, "ce": 5.728734970092773, "genuineness": 4.036643981933594, "identity": 0.6021239161491394, "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/emo_Distress/e2cca7fc776cd9d695b718e293a0699c87674d066e5934b7f3430cea148ccab4.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "e2ec9e07262c18f60580582c588639391035bd3ed3c0a5980dd0f5bb70dd3d80", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6e4984976efd5760fa63246e806d604613f0bd904c1733ce5d3d092df4dabc9b", "generation_seconds_batch": 15.736601160955615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08057913184165955, "target_z": -0.4628906268515054, "ce": 6.3641486167907715, "genuineness": 4.457139015197754, "identity": 0.5139996409416199, "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/emo_Distress/e2ec9e07262c18f60580582c588639391035bd3ed3c0a5980dd0f5bb70dd3d80.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": "e2f5d902dd540ad2943563e603f67b06d67b8fbafcdf9d2c99c4fb6afc700c2b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e4a41b9b95a42e6ea3e591ad733ddff99c855e9c55399c7c66cb6a24e34c446", "generation_seconds_batch": 15.800462553044781, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8600192070007324, "target_z": 2.937499958982034, "ce": 5.824047088623047, "genuineness": 3.653805732727051, "identity": 0.41494619846343994, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot verder, tot aan het kleine houten. Ik wacht. Aan de andere kant.", "wer": 0.19047619047619047, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/e2f5d902dd540ad2943563e603f67b06d67b8fbafcdf9d2c99c4fb6afc700c2b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "e3286091689d6bf7b5d9361b7dc336a40345b265ea9339f8b653d87ff53ae5a1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "1ba8aef251f8d285a5831dc0d7ebe71ff2ec65f461107fd447fa83ffba05a783", "generation_seconds_batch": 16.243462050915696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3408024311065674, "target_z": -0.1445312331940278, "ce": 5.895530700683594, "genuineness": 4.406930446624756, "identity": 0.6277952194213867, "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/emo_Distress/e3286091689d6bf7b5d9361b7dc336a40345b265ea9339f8b653d87ff53ae5a1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "e3335799e48620d6361bb71f3afbad82a73f80188e1449c3a6afbd49b581d689", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5308617541321d8a6d885eeca85300b92897c2b1e339f457ad0fb14079c2c220", "generation_seconds_batch": 15.352947362000123, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4986038208007812, "target_z": 3.718749797188946, "ce": 5.871703147888184, "genuineness": 3.9299514293670654, "identity": 0.3383011519908905, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast dit. Naast het oude raam. We kunnen er samen in kijken.", "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/emo_Distress/e3335799e48620d6361bb71f3afbad82a73f80188e1449c3a6afbd49b581d689.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "e3b296d30a82bb45b49f73a651bad79c1eafbd6c59c623d75358b9915d877636", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "49028178a07c593f410b5f54af3e6ed5ce3d3f2a3c8feebd25ab2f12c1f00fe7", "generation_seconds_batch": 21.66853577492293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.588005781173706, "target_z": 3.828124914545904, "ce": 5.383228778839111, "genuineness": 3.7542223930358887, "identity": 0.41782739758491516, "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/emo_Distress/e3b296d30a82bb45b49f73a651bad79c1eafbd6c59c623d75358b9915d877636.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "e3b7f280e9671b68c0d11c81edaa498b7bb7312ff65b932e4231b8d669547fae", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ea81ea13c3b94fb2e365bcf313193e5e08185e846fed6675f1ff34dbdbaf3f68", "generation_seconds_batch": 22.52061407698784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9111058712005615, "target_z": 2.999999817697929, "ce": 5.569881439208984, "genuineness": 3.9550557136535645, "identity": 0.36840271949768066, "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/emo_Distress/e3b7f280e9671b68c0d11c81edaa498b7bb7312ff65b932e4231b8d669547fae.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "e448bd172796d948f916dda473c64e139ddfc34f2fb36771e31fcc958a8c31f1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "970ebc4ab8842a6907d5c9f9b0fe396074d0aba77005a7aa50c792dc03c36d23", "generation_seconds_batch": 21.07076871301979, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.872790813446045, "target_z": 2.953124850740179, "ce": 5.514282703399658, "genuineness": 4.093128204345703, "identity": 0.5913538336753845, "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/manual-comparison-v1/audio/emo_Distress/e448bd172796d948f916dda473c64e139ddfc34f2fb36771e31fcc958a8c31f1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "e4838e5f70708a4f9145559b4c4132358ac440d84b077e51d3d19c48c220ee95", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bc3dae6584a121123eea454c017e51c31457847ff2b84698b153a16afa96c1e3", "generation_seconds_batch": 16.892990329070017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.949420928955078, "target_z": 3.0468747846556785, "ce": 5.748591423034668, "genuineness": 4.168440818786621, "identity": 0.03583543747663498, "hypothesis": "De deur staat nog open. Ik heb je juist op de stoel gelegd. Zeg maar wanneer je wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/e4838e5f70708a4f9145559b4c4132358ac440d84b077e51d3d19c48c220ee95.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "e4cd8116c19dc29a7ff56f29b5d0acd420a6a1c0a9c019a63059c339e49f1b2c", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "b6df267436c0c27f239eec6c08b39f63609593b6fcb027e54ae0249d9149417b", "generation_seconds_batch": 23.730859798029996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25140056014060974, "target_z": -0.2539062411697434, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.399488627910614, "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/emo_Distress/e4cd8116c19dc29a7ff56f29b5d0acd420a6a1c0a9c019a63059c339e49f1b2c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e4f306d75c15a6342706b332501a762beb3e906e7bb2f61e4b95e9308e7b7e8e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f077f041b177605fb0d280c5c3139cb2cb020322f8f43eabc43f33053be51607", "generation_seconds_batch": 21.975962900090963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2561899423599243, "target_z": -0.24804687030002473, "ce": 6.213237762451172, "genuineness": 4.337893962860107, "identity": 0.5693691968917847, "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/emo_Distress/e4f306d75c15a6342706b332501a762beb3e906e7bb2f61e4b95e9308e7b7e8e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "e507f901913fc8e7cd4e4cfda7bf4bc19fd3c72991e04618ce254f3fca155b64", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "fe616665c7c843087450d0c86f91c17cf9e457c8f942cbf0d55fb7236c0119d2", "generation_seconds_batch": 23.112864642986096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451324939727783, "target_z": 2.43749992252162, "ce": 5.7128496170043945, "genuineness": 4.394378662109375, "identity": 0.7988426685333252, "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/emo_Distress/e507f901913fc8e7cd4e4cfda7bf4bc19fd3c72991e04618ce254f3fca155b64.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "e5a6ff8ef1aaff5aa83f88d07490bc86c260af308932cec05987b5bccff182ac", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "1cecbe620de346701e3447d8179e65d964f71536cac7937732527f2a667df03a", "generation_seconds_batch": 21.66853577492293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1665399074554443, "target_z": 3.3124999863273445, "ce": 5.895530700683594, "genuineness": 4.243753433227539, "identity": 0.6208624839782715, "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/emo_Distress/e5a6ff8ef1aaff5aa83f88d07490bc86c260af308932cec05987b5bccff182ac.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e5b6704a977d1b0b4924354ff7878ad2d3a07d7b4bb0f476a6be29eda9f55898", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0e7c4198ee5c381c94d82dfdd8fae44b0bcd9f60fa80284ecec5735c7f71e12e", "generation_seconds_batch": 17.413138875039294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.1894097328186035, "genuineness": 4.118232727050781, "identity": 0.30998897552490234, "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/emo_Distress/e5b6704a977d1b0b4924354ff7878ad2d3a07d7b4bb0f476a6be29eda9f55898.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "e5e9432bde69f119721ba54381198e36880c4c69dde1e75f6e0592f09ef15842", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "208e3f210546afd703ba5a55ead4ec2bc40f3b9b232590acd9bee689dc9d2f4e", "generation_seconds_batch": 22.30942006490659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4461688995361328, "target_z": -0.015625001139387945, "ce": 6.229123115539551, "genuineness": 4.425758361816406, "identity": 0.24608610570430756, "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/emo_Distress/e5e9432bde69f119721ba54381198e36880c4c69dde1e75f6e0592f09ef15842.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "e5f85da6a7f853ff6e3ed1b169ea98e9412cbab208fe1f4e5e13ea83f32ca29e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6a74092f5079198e29436e8fdf4b9ed1acd51b7af96629dd55e8f802a3c88af7", "generation_seconds_batch": 17.038579487008974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4014679789543152, "target_z": -0.07031248689703863, "ce": 6.1894097328186035, "genuineness": 4.042920112609863, "identity": 0.20574800670146942, "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/emo_Distress/e5f85da6a7f853ff6e3ed1b169ea98e9412cbab208fe1f4e5e13ea83f32ca29e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "e63c97db8cf883e140c935fb9a12fe44c8dbcbf7195ace3dc89a5119fc33b219", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d10e4dd328f6024433d529f6a676bfcc07e7113c3e786cb270c9dd6662e553d9", "generation_seconds_batch": 22.600137372035533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3198001384735107, "target_z": 3.499999854158343, "ce": 6.141753673553467, "genuineness": 4.20609712600708, "identity": 0.2737790048122406, "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": 0.03999999999999915, "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/emo_Distress/e63c97db8cf883e140c935fb9a12fe44c8dbcbf7195ace3dc89a5119fc33b219.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "e6ae8b246dd7d0c7d0ec23914cdb3cae7445659d43aa43f691be01a144c113f9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bcfa839fc370043a0d6708cddc42ae0c1da34d81db1b2701912ddbb0306f54fa", "generation_seconds_batch": 16.294037680956535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7207603454589844, "target_z": 0.32031250512724574, "ce": 6.0305562019348145, "genuineness": 4.65797233581543, "identity": 0.5176949501037598, "hypothesis": "Die Tür ist noch offen. Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/e6ae8b246dd7d0c7d0ec23914cdb3cae7445659d43aa43f691be01a144c113f9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "e6c39674f6348edf061c693f83f31b87abf725d349a6c80a1b3acaebb534f459", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bade5dedee0e9c53ee0a32a77733ca87de80ee228b2e540ad120bf2b55429dfc", "generation_seconds_batch": 23.104672770947218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1537680625915527, "target_z": 3.2968748028858856, "ce": 5.538110733032227, "genuineness": 3.6914620399475098, "identity": 0.5187578201293945, "hypothesis": "La porte, t'es encore ouverte. Je posais ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi, Your Pont, monsieur, le valorcule. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 1.2222222222222223, "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/emo_Distress/e6c39674f6348edf061c693f83f31b87abf725d349a6c80a1b3acaebb534f459.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 128, "seconds_generated": 10.24, "mp3_sha256": "14bc6042edc32a68edb8512c4fe0c02185d5b463eb82f370c0a59118e110b26b", "generation_seconds_batch": 18.029937613056973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1396482288837433, "target_z": -0.3906249920242844, "ce": 6.41180419921875, "genuineness": 4.293961524963379, "identity": 0.38268667459487915, "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/emo_Distress/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "e72c9f8c9e246e7e0693298940bd0c45a1f8741d37ececb6e9da64599b04284f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "f608dd9e33065cc95b5e6f278e9fc1701fb6794636d1bd4ba2caeddf5b43b821", "generation_seconds_batch": 21.439444393035956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.059825122356414795, "target_z": -0.4882812582605626, "ce": 6.475345611572266, "genuineness": 4.645420074462891, "identity": 0.5897629261016846, "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/emo_Distress/e72c9f8c9e246e7e0693298940bd0c45a1f8741d37ececb6e9da64599b04284f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "e78f96781e0fac28868f41e90db51493f1a676943a858c3e115a8e734fd22ecf", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6098c0f16465177e5ec3c8a3ed2d15c4897932125b3994abbe5b5eb187d7eb45", "generation_seconds_batch": 13.697948400047608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 6.229123115539551, "genuineness": 3.7793264389038086, "identity": 0.46410271525382996, "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": 0.03999999999999915, "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/emo_Distress/e78f96781e0fac28868f41e90db51493f1a676943a858c3e115a8e734fd22ecf.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "e7b6c622e58622ddc8a8d1a2284adc222582fdcc567a26fe613e0b60f9c695eb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "41960e3d376302963ff909e25bd011fc583ed7199122fcca0214aa04ef9f2968", "generation_seconds_batch": 22.589266129070893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5024116039276123, "target_z": 2.4999997812375145, "ce": 5.696964263916016, "genuineness": 4.105680465698242, "identity": 0.24979321658611298, "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/emo_Distress/e7b6c622e58622ddc8a8d1a2284adc222582fdcc567a26fe613e0b60f9c695eb.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": "e7ec80a6e72622c687ed8e38c04cbe57896f4d750aa6d635abda1631234dc4d6", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "00f08acb71af45f98b34654b23aebd71413bb2a54a1d74195867c3668d96689c", "generation_seconds_batch": 20.515082628000528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 5.629451274871826, "genuineness": 3.5063188076019287, "identity": 0.4548642635345459, "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": 0.03999999999999915, "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/emo_Distress/e7ec80a6e72622c687ed8e38c04cbe57896f4d750aa6d635abda1631234dc4d6.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "e8837ef99f1c0f368b0d42f1f49e7f4d2a6daed5f90c13c5ebb30572b471f616", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bb8117446ef2c80e6d6640ff32b742345038a5ae0546a2a8812e394fc2b03553", "generation_seconds_batch": 23.413634181022644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2827149629592896, "target_z": 1.0078125552603154, "ce": 5.780362129211426, "genuineness": 4.18099308013916, "identity": 0.5461656451225281, "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/emo_Distress/e8837ef99f1c0f368b0d42f1f49e7f4d2a6daed5f90c13c5ebb30572b471f616.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "e887952cc346b1bcf851ed90d17aa3bcc3d70f32df30eace209707f6c51d462d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "849831af9ad86767038fbecbbed05a4cc5e3b331a5b95be59b0a9c9f074592ad", "generation_seconds_batch": 22.376354706007987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.8817546367645264, "target_z": 4.187499758449755, "ce": 5.260117053985596, "genuineness": 3.7542223930358887, "identity": 0.47214969992637634, "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/emo_Distress/e887952cc346b1bcf851ed90d17aa3bcc3d70f32df30eace209707f6c51d462d.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "4d451940064c529830b61eb00e641dd9f135a54818237d1a6285167fc852cb84", "generation_seconds_batch": 16.47733486199286, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10612252354621887, "target_z": -0.4316406245727295, "ce": 6.316492557525635, "genuineness": 4.281409740447998, "identity": 0.6510621309280396, "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/emo_Distress/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "e9ef68891c55a5fd701227e54d8909ba579d49d80e305868acb517ae714fb8fd", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ce9a7e4ae14d7986f4c9e00c474bdfb8cf37a896b678ab20aa1a67edf3f92da3", "generation_seconds_batch": 20.553879959974438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1537680625915527, "target_z": 3.2968748028858856, "ce": 5.307773113250732, "genuineness": 3.5314228534698486, "identity": 0.5035327076911926, "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": 0.03999999999999915, "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/emo_Distress/e9ef68891c55a5fd701227e54d8909ba579d49d80e305868acb517ae714fb8fd.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "ea71b25948f4a3c5037fe69287b7ca4d6549b013c90403407eb779875822ad03", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "66a93c7834c5cbdc88ce3cee60fea4508ffe8f0ce042ef5aa3ab50de80cde4a1", "generation_seconds_batch": 22.27198200300336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2443997859954834, "target_z": 0.9609374424609087, "ce": 5.879645347595215, "genuineness": 4.325342178344727, "identity": 0.5930328369140625, "hypothesis": "He encontrado la cajita. Estaba junto. La ventana vieja. Podemos mirar juntos lo que hay dentro.", "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/emo_Distress/ea71b25948f4a3c5037fe69287b7ca4d6549b013c90403407eb779875822ad03.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "eb4008472854e04b7922ba48ef9b59dd8020af78c1a3635cf3d566737f53c4c9", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "adad10c6edc078b00f91b8036f44784ea8b2a8d1a8353820404706004d2b6fdc", "generation_seconds_batch": 16.298488704953343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1619986891746521, "target_z": -0.36328124914545906, "ce": 6.316492557525635, "genuineness": 4.557555198669434, "identity": 0.34419018030166626, "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/emo_Distress/eb4008472854e04b7922ba48ef9b59dd8020af78c1a3635cf3d566737f53c4c9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "eb557f0de2019739c7763548dd8dc14b3781113b66899b847398a0168b4722f5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a88815321d2eb5efb1203fe99321af3ee424a34568afa5f1569923597e3008db", "generation_seconds_batch": 15.366882481030189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4685193598270416, "target_z": 0.0117187417394374, "ce": 6.157639026641846, "genuineness": 4.457139015197754, "identity": 0.6326755881309509, "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/emo_Distress/eb557f0de2019739c7763548dd8dc14b3781113b66899b847398a0168b4722f5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "ebae532a30d5f67ead679408835b33015cba1b8dcf5d1347160ba319de384260", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e0c91d12c1d4d847424147fd23c6bddca9511ac54990e0b69d50568857d5306c", "generation_seconds_batch": 22.881561273010448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.268961638212204, "target_z": -0.23242186916063678, "ce": 6.3641486167907715, "genuineness": 4.325342178344727, "identity": 0.509723961353302, "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/emo_Distress/ebae532a30d5f67ead679408835b33015cba1b8dcf5d1347160ba319de384260.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "ebca5c787932f718ad20324b50330d7506a9a9bd7b811156f70f86d75fcb1bca", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cb0e2c9abb1c7236c8c826d0f8c29097546f55df99c0a6131e0aba552161a379", "generation_seconds_batch": 21.13183899107389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.536918878555298, "target_z": 3.7656247641466956, "ce": 5.637393951416016, "genuineness": 4.055472373962402, "identity": 0.6598857641220093, "hypothesis": "La porte est encore tout coverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/ebca5c787932f718ad20324b50330d7506a9a9bd7b811156f70f86d75fcb1bca.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "58fcc132750bc8041005990af8349685a16ba29a1f105c20b1564d77ba13b070", "generation_seconds_batch": 14.757277628988959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4022662043571472, "target_z": -0.06933593116215456, "ce": 5.927301406860352, "genuineness": 4.193545341491699, "identity": 0.7861268520355225, "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/emo_Distress/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ebf9386e82f742719893433dd1fa8de74ec0247477c5a3d424a213fcd00c9de9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The road turns left behind the bridge.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cf449e0ef41018d49367e9392392525642fc13976cc4ac53f5b7a1be58a97bbb", "generation_seconds_batch": 16.532636835006997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4602887630462646, "target_z": 3.671874830231196, "ce": 5.629451274871826, "genuineness": 3.660081624984741, "identity": 0.47497981786727905, "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": 0.03999999999999915, "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/emo_Distress/ebf9386e82f742719893433dd1fa8de74ec0247477c5a3d424a213fcd00c9de9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "ec54e0793bbbb1d90c59b50ce0d56e803a2c9b5e4e69665cfce4dc1cdb1816ac", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "47e70369f54d79ae18091d5ef120402637ee9cf244db9c2706a0a86aa1249966", "generation_seconds_batch": 21.54455684009008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23224301636219025, "target_z": -0.27734374287882535, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.3405331075191498, "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": 0.03999999999999915, "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/emo_Distress/ec54e0793bbbb1d90c59b50ce0d56e803a2c9b5e4e69665cfce4dc1cdb1816ac.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "ec87ff3fe86afc9bf4017648ebeb306240af28827fbbed1dae522ef249cbc134", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "cd20b08140417ce1be88beb96398998ea8fae2d70bb0198cddec48734d664b5a", "generation_seconds_batch": 21.942727606045082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.695216953754425, "target_z": 0.28906250284846985, "ce": 6.0146708488464355, "genuineness": 4.432034492492676, "identity": 0.46433284878730774, "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/emo_Distress/ec87ff3fe86afc9bf4017648ebeb306240af28827fbbed1dae522ef249cbc134.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "ec9c9eb4484d4d352458b8987df103ce25ccc59946f2850ef1703fb5da46406a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "abb044d12be4071c6c6bb4f68e048860e84bf790d9d275cefa63a3b87a1581f0", "generation_seconds_batch": 15.421133280033246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.949420928955078, "target_z": 3.0468747846556785, "ce": 5.847874641418457, "genuineness": 3.961331605911255, "identity": 0.44656872749328613, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond augen ramen. We kunnen er samen in gaan kijken.", "wer": 0.2777777777777778, "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/emo_Distress/ec9c9eb4484d4d352458b8987df103ce25ccc59946f2850ef1703fb5da46406a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "ecfac09205ca653f52bf987efc35cbacc074e2eee9affdbc87a28f58df4d8e1e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "71a1894be3f0454a421e593eda41b2585660711f93f4566c3a43e451f947b024", "generation_seconds_batch": 21.415206364006735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7450737953186035, "target_z": 2.7968747664254714, "ce": 5.708878040313721, "genuineness": 4.124508857727051, "identity": 0.6262477040290833, "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/manual-comparison-v1/audio/emo_Distress/ecfac09205ca653f52bf987efc35cbacc074e2eee9affdbc87a28f58df4d8e1e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "ed1c0f185a7de6eeba0e0fc94204a42dc0d51d78d08667e3b96250415481df64", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "9e54c1bf710100951933babdb9b8506665c0ac21ee091d905b61085eb262efb2", "generation_seconds_batch": 20.657408007071353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5834646224975586, "target_z": 0.1523437519939289, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.5256122350692749, "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/emo_Distress/ed1c0f185a7de6eeba0e0fc94204a42dc0d51d78d08667e3b96250415481df64.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "ed531feb7285d51e0dec503d3ae03e68ca712a5e36c74c67fa6957c65d3a35c0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7a7041a9bc2c7fedfe5ed7912c50883875a9e2b6f2ffbd9d9c869614864c3b53", "generation_seconds_batch": 21.562189968070015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21947132050991058, "target_z": -0.29296874401821327, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.5178045630455017, "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": 0.03999999999999915, "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/emo_Distress/ed531feb7285d51e0dec503d3ae03e68ca712a5e36c74c67fa6957c65d3a35c0.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": "ed64f406d54bb5d719bbc55f84fa16a9c11ac0dfbb345da476c64d2462e3b978", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d102e818662e892e4905c513bc559409a424afdbf5c16ea203d39ade40c05085", "generation_seconds_batch": 18.187164644012228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.013279438018799, "target_z": 3.1249998268130326, "ce": 5.307773113250732, "genuineness": 3.7165660858154297, "identity": 0.3762051463127136, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, 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/emo_Distress/ed64f406d54bb5d719bbc55f84fa16a9c11ac0dfbb345da476c64d2462e3b978.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": "edbe6b29500da5857cab35f9bd0c6705707d24c62832fb20574254a48befec3a", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4e078d5c66916150fe72fbb4e8282a656f8352fd7910286653fa8b9221cb5281", "generation_seconds_batch": 20.440868919948116, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5752341747283936, "target_z": 3.812500022787759, "ce": 5.289902210235596, "genuineness": 3.71028995513916, "identity": 0.7494238018989563, "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": 0.03999999999999915, "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/emo_Distress/edbe6b29500da5857cab35f9bd0c6705707d24c62832fb20574254a48befec3a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "edd6f63923c287720776fe56978892b3098d0807eb8dbf0a202cfbe03b29aa59", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d6862eba5abba82d93047cf959bb641bedad4ce061259f1d34b508725b9c0e2c", "generation_seconds_batch": 22.11551482998766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.540726661682129, "target_z": 2.5468747481952643, "ce": 5.704906940460205, "genuineness": 3.9927117824554443, "identity": 0.35143813490867615, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/edd6f63923c287720776fe56978892b3098d0807eb8dbf0a202cfbe03b29aa59.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "efe6814fcb3be56be340f41ffad8245a5cab9a96f3b40257fa8980cf1f244a89", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a07b1431f3f6262a9b2ce904df9301c524dceb8a65f4c7151dcbd530dddfda6b", "generation_seconds_batch": 14.539664278039709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0260512828826904, "target_z": 3.1406250102544915, "ce": 5.728734970092773, "genuineness": 3.961331605911255, "identity": 0.2927853465080261, "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/emo_Distress/efe6814fcb3be56be340f41ffad8245a5cab9a96f3b40257fa8980cf1f244a89.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "f054b1ba63a2a6a4615dc8aed0944261fb3084ac635b2e06232c7906284422d4", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "467427ba69227a7e52581a899243c3d9aa10569e8ff692d7644ff62631b1062a", "generation_seconds_batch": 21.90512177196797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8804064989089966, "target_z": 0.5156249646789737, "ce": 5.847874641418457, "genuineness": 4.532451152801514, "identity": 0.5881112217903137, "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/emo_Distress/f054b1ba63a2a6a4615dc8aed0944261fb3084ac635b2e06232c7906284422d4.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": "f096dc59cc08980fdd6d6d2be8197f45f4318f8e943f9ddb2c114b7ab2edbca9", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b64a0a93ac30a3920d45c7c397fe42c3f853c206386586f68081bd1c483479e1", "generation_seconds_batch": 17.056003556004725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0554025173187256, "target_z": 1.9531250695026647, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.3513339161872864, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier. Naast de hoge boekenkast. We zetten het naar de lunch terug.", "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/emo_Distress/f096dc59cc08980fdd6d6d2be8197f45f4318f8e943f9ddb2c114b7ab2edbca9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "f0e0a5823f8e29c7175d89e204b725ce36e58ff38bbc345877e4275c18424d6b", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "471ede46cdc83707cc696493373c779658a74ef7816dc91ee7413cb2b15b2f81", "generation_seconds_batch": 21.896303591900505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39508211612701416, "target_z": -0.07812500569693973, "ce": 6.022613525390625, "genuineness": 4.306513786315918, "identity": 0.6039496660232544, "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/emo_Distress/f0e0a5823f8e29c7175d89e204b725ce36e58ff38bbc345877e4275c18424d6b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "f15a02d98b6b67c4254dd0bc2a0d38d02452d70dff2647564aad1fd5b46b0c38", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "60810997da25621bcf41d801d71e6622a0bfb37cea1ed6dfd5d542e6f78b7aa1", "generation_seconds_batch": 22.528873822069727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1409964561462402, "target_z": 3.2812499111277402, "ce": 5.839932441711426, "genuineness": 4.256305694580078, "identity": 0.8305593132972717, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "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/emo_Distress/f15a02d98b6b67c4254dd0bc2a0d38d02452d70dff2647564aad1fd5b46b0c38.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "f174e502ed27e19ff92ddba846fd33a0c79ab8898084e341ec78e905c66d363d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "53edfb6fd6b8f94f672608ba706c36fc2a5d26b4c0e3363cec83bf2879876709", "generation_seconds_batch": 22.600137372035533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.642900228500366, "target_z": 2.6718747573103676, "ce": 5.5738525390625, "genuineness": 3.553389072418213, "identity": 0.5395466089248657, "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": 0.03999999999999915, "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/emo_Distress/f174e502ed27e19ff92ddba846fd33a0c79ab8898084e341ec78e905c66d363d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "f1b5cde8f7eb47429300ded25861d8db864eae19e709e8bf74540a6fa638d26e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "84478c73017f74b94307e98974b29a088e4e6d1839ce9a1b6393066d2daa82ba", "generation_seconds_batch": 19.77973629999906, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2942566871643066, "target_z": 3.4687497789587387, "ce": 4.958295822143555, "genuineness": 3.512594699859619, "identity": 0.4729999899864197, "hypothesis": "J'ai trouvé la petite boîte. Elle était prête à vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "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/emo_Distress/f1b5cde8f7eb47429300ded25861d8db864eae19e709e8bf74540a6fa638d26e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "f20e6097478d7927a39449ef4f35eca7e704e4093cafc105cd2270a775431fd3", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ffc4418eea14b1ac552e16f4afa8eb964c8cbc7c7d38379d272fa58f8d04e0cc", "generation_seconds_batch": 14.62552785500884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1409964561462402, "target_z": 3.2812499111277402, "ce": 5.685050010681152, "genuineness": 3.760498285293579, "identity": 0.32863765954971313, "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/emo_Distress/f20e6097478d7927a39449ef4f35eca7e704e4093cafc105cd2270a775431fd3.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "43fb8106cdefdd0f1b3c9815821227e27cd1eb34b675c9e672cb20fcbead3b76", "generation_seconds_batch": 15.175397929968312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16838452219963074, "target_z": -0.35546876680597217, "ce": 6.062326908111572, "genuineness": 4.557555198669434, "identity": 0.7014206647872925, "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/emo_Distress/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "f2488f90d5389c1e41b7d9f2cfe5c1b4cce41e44eb1d74b25a14e40a234a211f", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "4e13f9dcb79a3075070072c5c1cf306fb13d601f0c04d6f0a5c12b3ea38e8983", "generation_seconds_batch": 21.778745813993737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21308547258377075, "target_z": -0.3007812445879073, "ce": 6.149696350097656, "genuineness": 3.9173994064331055, "identity": 0.3677913546562195, "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/emo_Distress/f2488f90d5389c1e41b7d9f2cfe5c1b4cce41e44eb1d74b25a14e40a234a211f.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "f258c2be7e8cc712c507806de5166eb0b5175d8120503cf31763ec9b3657fcf0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e5af50e8bdb0934346050c2fbeaa2ffea6a1beb0daebd69280a230a766aabd7e", "generation_seconds_batch": 13.929408598109148, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23543593287467957, "target_z": -0.27343750170908193, "ce": 6.09409761428833, "genuineness": 4.65797233581543, "identity": 0.6052114963531494, "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/emo_Distress/f258c2be7e8cc712c507806de5166eb0b5175d8120503cf31763ec9b3657fcf0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "f3a9d7a7e9b78ba50523e79d2be4ecec51ad365e64b28d14876afa471d835cfb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "ccc277370bfe23ccb115bfb04eaf2c8d29e6052751e246571e01e8dc6e28062f", "generation_seconds_batch": 22.881561273010448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2418217808008194, "target_z": -0.2656250011393879, "ce": 6.213237762451172, "genuineness": 4.193545341491699, "identity": 0.5216274261474609, "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/emo_Distress/f3a9d7a7e9b78ba50523e79d2be4ecec51ad365e64b28d14876afa471d835cfb.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f3c35f520d2cc614de87d4ac1bbcee554ec1e68db8124679c131876693a8ab22", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "1cd002ba5237f8ec0abf141a2bc059423af2a985c51c1001130574d71160ea64", "generation_seconds_batch": 20.29927638405934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.115453004837036, "target_z": 3.249999835928136, "ce": 5.387199878692627, "genuineness": 3.653805732727051, "identity": -0.07462410628795624, "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/emo_Distress/f3c35f520d2cc614de87d4ac1bbcee554ec1e68db8124679c131876693a8ab22.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "f3c6863d03c555b4868e872fa8a5f0ab253a89fc5a4baef41f3bf7d807508d94", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4d96b91fab2a54de03f8077a9d1a64e003aab917ff8170eae973c5b07b961e7a", "generation_seconds_batch": 22.510182866011746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.72849440574646, "target_z": 3.9999998906187573, "ce": 5.657250881195068, "genuineness": 3.7416701316833496, "identity": 0.7261456251144409, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo, listo, listo. Mamí, ¿cuándo estás listo?", "wer": 0.4, "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/emo_Distress/f3c6863d03c555b4868e872fa8a5f0ab253a89fc5a4baef41f3bf7d807508d94.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": "f3df620474bc17ca71e7e12423f19e2ad550435c06f81651d64694168c0fd94b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4b8506c765377549e0eb4172bf8d7e2d277f1e02bdaab1b495a8fd40fb1cd419", "generation_seconds_batch": 20.64027615392115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.08610200881958, "target_z": 4.437500068363277, "ce": 5.903473377227783, "genuineness": 3.760498285293579, "identity": 0.6631314754486084, "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/emo_Distress/f3df620474bc17ca71e7e12423f19e2ad550435c06f81651d64694168c0fd94b.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": "f3dfea5608a7d53872035af06d81ba21b3ae8c947948ba460d581cb54f78a124", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4abcf42b449a11b80964f8913facf62fa3ec98647a70aca7ffb63347f6b3a98f", "generation_seconds_batch": 25.090171106974594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451324939727783, "target_z": 2.43749992252162, "ce": 5.4944257736206055, "genuineness": 3.6851859092712402, "identity": 0.3395218551158905, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suche 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/emo_Distress/f3dfea5608a7d53872035af06d81ba21b3ae8c947948ba460d581cb54f78a124.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "f4233fdd12ee09ff6ebe548c4503b238acb79991e507412934bc3bb1327fee09", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4fd49e6b4c90c7354eb2d8a157cbe01fc5cdbcd3766c4db9a4fb6dd580962526", "generation_seconds_batch": 22.551244683098048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.089909553527832, "target_z": 3.2187497607285316, "ce": 6.173524379730225, "genuineness": 3.9048471450805664, "identity": 0.47997814416885376, "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": 0.03999999999999915, "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/emo_Distress/f4233fdd12ee09ff6ebe548c4503b238acb79991e507412934bc3bb1327fee09.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "f4a6e4c5cfa7606f579770f85bb69d2c340a5c80fcd61ee32825a99c7fa36d32", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "b1686789e1dc07db69b8fc4d8c24e3a1b5c5ee9e360c6d4846572a7011679770", "generation_seconds_batch": 15.060581807047129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9851582050323486, "target_z": 1.867187581466238, "ce": 6.046441555023193, "genuineness": 4.507347106933594, "identity": 0.6829033493995667, "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/emo_Distress/f4a6e4c5cfa7606f579770f85bb69d2c340a5c80fcd61ee32825a99c7fa36d32.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "f4c1a859b8223619f0c17feae0a70202264068d1ad50facd139fe90fe280bf82", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d263b5d0f447820f9a73d16d3565c4287e86d6cc6453fbd34bde1bffcb75b912", "generation_seconds_batch": 16.129107884014957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8855626583099365, "target_z": 2.9687500341816384, "ce": 5.696964263916016, "genuineness": 4.005263805389404, "identity": 0.48165014386177063, "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/emo_Distress/f4c1a859b8223619f0c17feae0a70202264068d1ad50facd139fe90fe280bf82.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f4c353422674720aeadb52deb94111c06a843aa16b4de6d3517deefdfc8d631c", "bucket": "emo_Distress", "phase": "wording", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "a4ee9a0ea194218187158ce93c7a46ae71f8860b90f377bf6f54bd9aa21a49af", "generation_seconds_batch": 13.995535591966473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4295893907546997, "target_z": 1.1874999772122412, "ce": 6.09409761428833, "genuineness": 4.507347106933594, "identity": 0.5927358865737915, "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/emo_Distress/f4c353422674720aeadb52deb94111c06a843aa16b4de6d3517deefdfc8d631c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "f4c6053e81659b10041d908e6627f67c5283e80c92c1390faf103dabe3e5ec30", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "49719d2b0a504fc6694bca8abd00e4366073c4aabd135957778fc48324924822", "generation_seconds_batch": 22.073566458071582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4130098819732666, "target_z": 2.39062495556387, "ce": 5.355429172515869, "genuineness": 3.886019229888916, "identity": 0.5681841373443604, "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/emo_Distress/f4c6053e81659b10041d908e6627f67c5283e80c92c1390faf103dabe3e5ec30.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": "f4cc0f6b09a0cd442ea1e7352890f5c487d71f1b071f2338f480a1c7d71c81c0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3cc675ba27e68122439d30f2a76fe775ae76fc9f61160f50eaa48a02f066869c", "generation_seconds_batch": 22.432491926010698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 4.724686622619629, "target_z": 5.218749906570189, "ce": 5.140976905822754, "genuineness": 3.6098732948303223, "identity": 0.5030441284179688, "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/emo_Distress/f4cc0f6b09a0cd442ea1e7352890f5c487d71f1b071f2338f480a1c7d71c81c0.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "f4e43321f928d0e4b85fa80bf59b296825d3417cf47d76e0609c75a527eed11e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e46ff0f2c1c9fdd2bedb320648d5f055783e5e31bbd081a2e7bc3e9e9ee0b3b1", "generation_seconds_batch": 18.839293269906193, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.204854965209961, "target_z": 3.3593749532850943, "ce": 5.855817794799805, "genuineness": 4.080576419830322, "identity": 0.3574486970901489, "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/emo_Distress/f4e43321f928d0e4b85fa80bf59b296825d3417cf47d76e0609c75a527eed11e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "f5064b289921c56be1d22e763db68d412634be8e67414d8051fe56eb4d1f4bda", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "79ec256a2c6bd7526833ab1dfb1a75f72bed2ccb5e8ec106391d8c274c323e9b", "generation_seconds_batch": 22.30942006490659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7207603454589844, "target_z": 0.32031250512724574, "ce": 6.141753673553467, "genuineness": 4.3881025314331055, "identity": 0.6060945987701416, "hypothesis": "Ik heb het kleine toosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "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/emo_Distress/f5064b289921c56be1d22e763db68d412634be8e67414d8051fe56eb4d1f4bda.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "f5369d00f4d709d7c6485dd8a5b61fbf3c1aa0eb4a2b1d11ebe7c4c509e89f1e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "2c1c8eed0b3b8aadc0a0e7fe38d5cb77c42dacfb60ebb9028c530b04521c7a5b", "generation_seconds_batch": 22.070430728956126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37273165583610535, "target_z": -0.10546874857576508, "ce": 6.141753673553467, "genuineness": 4.507347106933594, "identity": 0.36994147300720215, "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/emo_Distress/f5369d00f4d709d7c6485dd8a5b61fbf3c1aa0eb4a2b1d11ebe7c4c509e89f1e.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "f587cd36cc3f4ee55bf86ccff0e789c14eb58194eaab9f33cf526343e3ff462d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "188ab00a9523c85227393e872ca34af83d6f05a840de27d1369796b4a7146347", "generation_seconds_batch": 22.916819524019957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13326236605644226, "target_z": -0.3984375108241855, "ce": 6.2767791748046875, "genuineness": 4.758388519287109, "identity": 0.6890609264373779, "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/emo_Distress/f587cd36cc3f4ee55bf86ccff0e789c14eb58194eaab9f33cf526343e3ff462d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-1", "key": "f6a0489fb035d4b328d5a9a1c6c5213929be8e770bedc6091e0981e7a0b6a966", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] I found the little box.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] It was beside the old window.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "953bc8ff1476fa62b5f4693516e8511d4b4ccdb64421dcfc7a90522f84e93011", "generation_seconds_batch": 22.225947962026112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22905008494853973, "target_z": -0.2812500022787759, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.4149898588657379, "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/emo_Distress/f6a0489fb035d4b328d5a9a1c6c5213929be8e770bedc6091e0981e7a0b6a966.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "f6cf76d13bcf13c00c81798b4f36133c758d66e31fb11adfe2e16c85bb9762d1", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "391570d0c9609312a36a2d34481112cda723f1e67b26ef0681f6f6ebe568783a", "generation_seconds_batch": 17.63829254102893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2725212574005127, "target_z": 2.218749979491017, "ce": 5.4666266441345215, "genuineness": 4.124508857727051, "identity": 0.4788879156112671, "hypothesis": "He encontrado la cajita. Estaba junto. La ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/f6cf76d13bcf13c00c81798b4f36133c758d66e31fb11adfe2e16c85bb9762d1.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f6e94d9d302b6ba7a5e2586a3ce1e2e5d492c736beeb45ac2e4679b873c6f83d", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "572eb12c8e304df8e8543684079a430b3ebbcc45dfa30dad5e493a24a6de3216", "generation_seconds_batch": 21.450732139055617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8127403259277344, "target_z": 1.6562500843147079, "ce": 6.1894097328186035, "genuineness": 4.231201171875, "identity": 0.5903533697128296, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent. De deur staat nog open. Ik heb je jas gegelegd.", "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/emo_Distress/f6e94d9d302b6ba7a5e2586a3ce1e2e5d492c736beeb45ac2e4679b873c6f83d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "f76139d0e8a0ac6fe99c5f710bc4643dc32fbdb4dd1106073dd4b9087c0db886", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "8c9a3d735d75ff98bb51cfba46037317aa86fe8e2fccff19785e384190a41b45", "generation_seconds_batch": 22.05221380002331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11091190576553345, "target_z": -0.42578125370301084, "ce": 6.284721851348877, "genuineness": 4.7332844734191895, "identity": 0.5610196590423584, "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/emo_Distress/f76139d0e8a0ac6fe99c5f710bc4643dc32fbdb4dd1106073dd4b9087c0db886.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f77e2d3aafcf5c9fcebe52165bda1065a14ab66f6dae5ecbd84558b88c1d6301", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f11575f4d0899f189b840a18b35f720f9981ce34e4b9273cbad23515ad53c04f", "generation_seconds_batch": 14.34858529700432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.451324939727783, "target_z": 2.43749992252162, "ce": 5.637393951416016, "genuineness": 4.093128204345703, "identity": 0.5209548473358154, "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/emo_Distress/f77e2d3aafcf5c9fcebe52165bda1065a14ab66f6dae5ecbd84558b88c1d6301.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "b4c579e79365ac096d2141cfa91c13d3a6193b1f57e891b869da7378a8d6a5bb", "generation_seconds_batch": 17.333966215956025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14603406190872192, "target_z": -0.3828125096847975, "ce": 6.260893821716309, "genuineness": 4.557555198669434, "identity": 0.6422882080078125, "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/emo_Distress/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "f7bc99cffe2d7589969ea010988f3b73ac0f6a4f631cb393f64c6b5076ebe7f5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "eb9201dbb5e86605355aeb765782d8f35e5877b4035ac7a39c554bd7204d5591", "generation_seconds_batch": 15.247200058074668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26736515760421753, "target_z": -0.23437501709081918, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.5335819721221924, "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/emo_Distress/f7bc99cffe2d7589969ea010988f3b73ac0f6a4f631cb393f64c6b5076ebe7f5.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": "emo_Distress", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": "146019b797e4b206a1a3433247bf303a1b546039adba0ffa145ec399f3677a02", "generation_seconds_batch": 16.00143401697278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11410483717918396, "target_z": -0.4218749943030603, "ce": 6.197352409362793, "genuineness": 4.18099308013916, "identity": 0.5391225218772888, "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/emo_Distress/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "f880421c8d9a649cafa0057c5147fa5de37008ac049519ec1583164d2c74fc77", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "ce8ca86722af2187ec541ff549d9d92f606d5577ed90d6f9c43db96187f70da4", "generation_seconds_batch": 23.067785097984597, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.042630672454834, "target_z": 1.9374998860612056, "ce": 5.700935363769531, "genuineness": 3.8420867919921875, "identity": 0.22124972939491272, "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/emo_Distress/f880421c8d9a649cafa0057c5147fa5de37008ac049519ec1583164d2c74fc77.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f8ef9ee851ab1d83e6c126569b2c3434285a36793b219a2f059ec0ad204b8d48", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "e72de90ae3e036514104ef6e96e9941531dcf6f6c77b9807ba2be657648a58ae", "generation_seconds_batch": 22.161793753039092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9378791451454163, "target_z": 0.5859374880364265, "ce": 6.070269584655762, "genuineness": 4.3881025314331055, "identity": 0.38671326637268066, "hypothesis": "Uw 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/emo_Distress/f8ef9ee851ab1d83e6c126569b2c3434285a36793b219a2f059ec0ad204b8d48.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": "f921cf0d070bfc93e8136db73efd148c3feee740e50f5d98a9454f2255ae38c7", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6a0b63564f962c07fa92458d031366197cd48f63a514119d95fd3fceb66fa7e9", "generation_seconds_batch": 21.421208717045374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6007773876190186, "target_z": 3.843749806304049, "ce": 5.8875885009765625, "genuineness": 3.5345609188079834, "identity": 0.009213965386152267, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk de la. En daarna is het raam. Neem ze mee als je weggaat.", "wer": 0.13636363636363635, "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/emo_Distress/f921cf0d070bfc93e8136db73efd148c3feee740e50f5d98a9454f2255ae38c7.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-0", "key": "f9461fc4e14840abd249d7834f03abe45d0543c1e1b767269e409dbfa5ba73d0", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De deur staat nog open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f1aef5afcb6c352d2f467501ce5eb68610892537512f603884a59002a90f66a4", "generation_seconds_batch": 21.911887869006023, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.349151372909546, "target_z": 2.312499913406516, "ce": 5.589737892150879, "genuineness": 3.9801597595214844, "identity": 0.4691251218318939, "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/emo_Distress/f9461fc4e14840abd249d7834f03abe45d0543c1e1b767269e409dbfa5ba73d0.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": "f9912826e4c4620e39ae0bf4cb105be7363152450ffa3165b61958bb8457bc0b", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37b96e184719c6eb66ad0f33088e25931eb5c4fa1c61b52d57fa2d275af85d05", "generation_seconds_batch": 21.05562697898131, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2431700229644775, "target_z": 3.406249920242844, "ce": 4.726469039916992, "genuineness": 3.578493118286133, "identity": 0.472323477268219, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Lassi zweimal legte ich das Handy weg. Sag mir, wann ihr reden könnt.", "wer": 0.25, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Distress/f9912826e4c4620e39ae0bf4cb105be7363152450ffa3165b61958bb8457bc0b.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "f9953452ecdd217f243e7cbc69eafc7707785106f3993a441a36ba20ecfa88e5", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "3c4e862028fe144745de5b0db41c52c48bfb006726f4a3b57ca9db4d2b6500f3", "generation_seconds_batch": 20.44515813200269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3210300207138062, "target_z": 1.054687522218065, "ce": 5.959072113037109, "genuineness": 4.406930446624756, "identity": 0.5776673555374146, "hypothesis": "Die Tür ist doch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/f9953452ecdd217f243e7cbc69eafc7707785106f3993a441a36ba20ecfa88e5.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "fa0471a3c58a63de61b951d8e914f6c503b381c17d384c5829581a4b274b6bed", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "6ff9b1e5f026fa91340f6773755f573c48eba16a9926d787564bd997163e2b3e", "generation_seconds_batch": 26.07599109702278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29530325531959534, "target_z": -0.2001953111469768, "ce": 6.300607204437256, "genuineness": 4.65797233581543, "identity": 0.6458641886711121, "hypothesis": "Ich hab die kleine Schachtel 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/emo_Distress/fa0471a3c58a63de61b951d8e914f6c503b381c17d384c5829581a4b274b6bed.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "fa28b0d035198882d50c2296762c339d077bdc11bbdecc44eac9f45eb677a4a2", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "91ba70f7f0c8602d7b2b1d19264df1e44bb77f499d8cb938370a73c20a8678de", "generation_seconds_batch": 24.117108173086308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6417354941368103, "target_z": 0.22363283108626586, "ce": 6.078212261199951, "genuineness": 4.482243061065674, "identity": 0.5862377882003784, "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/emo_Distress/fa28b0d035198882d50c2296762c339d077bdc11bbdecc44eac9f45eb677a4a2.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "fa40c7e56d138b323ee48f87ff86db43beca39fd8ec87d903675160850e10ec9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "996dfca63f317d8319ec58e57f1ff2885fbf128d840956b803405de07d253a4b", "generation_seconds_batch": 20.961575507069938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.285292863845825, "target_z": 2.234374871249162, "ce": 6.24500846862793, "genuineness": 4.425758361816406, "identity": 0.5308694243431091, "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": 0.03999999999999915, "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/emo_Distress/fa40c7e56d138b323ee48f87ff86db43beca39fd8ec87d903675160850e10ec9.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": "fae7fe85b1127941358216dd2da370022c843d644af2256eb8cabb7d072b9254", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e41ab32b9e4828a04df8408bbef2024e9014519c5640ffdd03b7c71a3b30f505", "generation_seconds_batch": 15.746242263005115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0515944957733154, "target_z": 3.171874793770782, "ce": 6.109982967376709, "genuineness": 3.6475296020507812, "identity": 0.25452667474746704, "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/emo_Distress/fae7fe85b1127941358216dd2da370022c843d644af2256eb8cabb7d072b9254.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "fb4d0c665989441259125a49ed3be720d6482536e8d641b4f15728c84df210e9", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bcc4e654d8db74768c5d84d92df08bbb8989d39b7bbf462e9983e94883dc347e", "generation_seconds_batch": 15.598624182981439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4730606079101562, "target_z": 3.6875000136726555, "ce": 5.780362129211426, "genuineness": 4.080576419830322, "identity": 0.5754076838493347, "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/emo_Distress/fb4d0c665989441259125a49ed3be720d6482536e8d641b4f15728c84df210e9.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-0", "key": "fb6710555d69c9b1e479f1552475c0da33549feaaa35de634a5a3708d8572499", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Die Tür ist noch offen.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ce242b1075d504ebef460967b9bf1a9a1d0e3ef0e565c7c53ad1efeacda2bbda", "generation_seconds_batch": 21.67572642909363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.591813564300537, "target_z": 2.609374898594473, "ce": 5.7406487464904785, "genuineness": 4.356721878051758, "identity": 0.554275393486023, "hypothesis": "Die Tür ist noch offen. Ich hab dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/fb6710555d69c9b1e479f1552475c0da33549feaaa35de634a5a3708d8572499.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": "fb687f420fda2aa172a800c270de1760a35e16c4d2d6e3383d5eb063a5741e5c", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5de7d1506dac44cbdaa9b3a29c2a3762180ba7641dcd04ce521e8fef6a7279bf", "generation_seconds_batch": 16.447657427052036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3836586475372314, "target_z": 3.578124896315697, "ce": 5.418970584869385, "genuineness": 3.8671910762786865, "identity": 0.743464469909668, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi, comment pour parler ?", "wer": 0.14285714285714285, "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/emo_Distress/fb687f420fda2aa172a800c270de1760a35e16c4d2d6e3383d5eb063a5741e5c.mp3" }, { "id": "emo_Distress-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": "emo_Distress-de-1", "key": "fbd537532f78582851d54ae349e5b7e143b4979a5c8e17e636032f505f6d1c27", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "f2dea4f85719752f7bdbcdfad40589a7983d7f5030c88e679932a75761fe4425", "generation_seconds_batch": 22.11551482998766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9660006761550903, "target_z": 1.8437500979873633, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.641359806060791, "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/emo_Distress/fbd537532f78582851d54ae349e5b7e143b4979a5c8e17e636032f505f6d1c27.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": "fc7c479de66997016f67154a041988191c928cdfff3d80d3df600dce847a13db", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f75d3c18856cd06524db872476070dba725c4c802349bfb56d09751f69edbb7", "generation_seconds_batch": 16.99001612898428, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.771847128868103, "target_z": 0.3828125096847975, "ce": 5.677107334136963, "genuineness": 4.21237325668335, "identity": 0.6199949979782104, "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/emo_Distress/fc7c479de66997016f67154a041988191c928cdfff3d80d3df600dce847a13db.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "fd57f0935242f0de2b9d228671e794a8872d114afad2f0541f8269377b00cce8", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "5718285e0b5bd9ae7fb93927051610a11743d720a0c318d452d418a6802b056c", "generation_seconds_batch": 24.18006433802657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4844839870929718, "target_z": 0.03125000227877589, "ce": 6.022613525390625, "genuineness": 4.68307638168335, "identity": 0.6333261132240295, "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/emo_Distress/fd57f0935242f0de2b9d228671e794a8872d114afad2f0541f8269377b00cce8.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "fd86f7a2f84781621348d1a77cdf45a7744024106eb4ed97364b89d91be89b8a", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "fc4bd41d149e89390feee2e19d399835c08383b4b7d7117147cd3a0de77336b5", "generation_seconds_batch": 17.141835490008816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3721168041229248, "target_z": 1.1171875267756166, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.8007257580757141, "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/emo_Distress/fd86f7a2f84781621348d1a77cdf45a7744024106eb4ed97364b89d91be89b8a.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-0", "key": "fd8e3723573b36db4f4e3b4fc45ba9f9948ab7c994dac741d9030c1f20d54a73", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La puerta sigue abierta.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "6d848e5dbe24af4471c62612607a115095ab4c375b7b9ea4df825118c37da691", "generation_seconds_batch": 14.72060722799506, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5227990746498108, "target_z": 0.07812500569693973, "ce": 6.109982967376709, "genuineness": 4.557555198669434, "identity": 0.47006478905677795, "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/emo_Distress/fd8e3723573b36db4f4e3b4fc45ba9f9948ab7c994dac741d9030c1f20d54a73.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "fdeaca7eec2b720297a7378d6dc75fd08e39a6418835463f1e82a5580a96c175", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4220b3cc7ae97cd86ff55620ef5f1b74ea9658c5f16ccf9e92dd038c4766904e", "generation_seconds_batch": 22.073566458071582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.234206199645996, "target_z": 2.1718750125332673, "ce": 5.927301406860352, "genuineness": 3.860914945602417, "identity": 0.4407706558704376, "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/emo_Distress/fdeaca7eec2b720297a7378d6dc75fd08e39a6418835463f1e82a5580a96c175.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "fe7a9a2e9f629a32ca604b7079d6048420f66631aeae386c018e629bb893867e", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5cb8c85135a443f197b3712e55eae9112ed6098a5759c674fc457387cb145197", "generation_seconds_batch": 22.058213534997776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0298590660095215, "target_z": 1.9218749943030602, "ce": 5.764476776123047, "genuineness": 4.193545341491699, "identity": 0.6739273071289062, "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/manual-comparison-v1/audio/emo_Distress/fe7a9a2e9f629a32ca604b7079d6048420f66631aeae386c018e629bb893867e.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": "fe9b87c0281f4d332e3cf035447cf02b413756c8bae38383b4739e96810068a0", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Your message arrived after I had left.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e6e34a43fa31035a77f0a4d8fa087e75a0eb34cda112fc8afc2a534da49cc96", "generation_seconds_batch": 21.442088808049448, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.562462329864502, "target_z": 3.7968748393463, "ce": 6.260893821716309, "genuineness": 3.7918784618377686, "identity": 0.5083684325218201, "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/emo_Distress/fe9b87c0281f4d332e3cf035447cf02b413756c8bae38383b4739e96810068a0.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": "feaf07f54de287da9805677e90e8d0753c2f667198496dda6cb2d0a7791f5287", "bucket": "emo_Distress", "phase": "heldout", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a4e223560097f36a930f95533878715589e76a3f1a847a88a08c521e97a73cc5", "generation_seconds_batch": 15.782312460942194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.425781488418579, "target_z": 2.4062498473220155, "ce": 6.022613525390625, "genuineness": 4.256305694580078, "identity": 0.44923314452171326, "hypothesis": "Ich schrieb die Nummer auf den Umschlag. Lies sie genau und prüfe die letzten beiden Ziffern. Ruf an, wann 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/emo_Distress/feaf07f54de287da9805677e90e8d0753c2f667198496dda6cb2d0a7791f5287.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "feb5d99c3ce3d31a097b3e65275c800bffb83a9b2bd8cb306e8fc97c7cb5d982", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "14762931609cc2ea01a7aeb0a9598f6420e47ace1f38d23455c7fc01ab060a5e", "generation_seconds_batch": 22.185328477993608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5764639377593994, "target_z": 1.3671875450058237, "ce": 5.824047088623047, "genuineness": 3.9550557136535645, "identity": 0.32881665229797363, "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/emo_Distress/feb5d99c3ce3d31a097b3e65275c800bffb83a9b2bd8cb306e8fc97c7cb5d982.mp3" }, { "id": "emo_Distress-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": "emo_Distress-es-1", "key": "fec1b833695c30433dea0b86dfd3b71cb6c1928a013f9931b61bb58fadeb3f55", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] He encontrado la cajita.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "d50091390a8a573494edf09980b15dd272c7975c293c0fa4fea43bda5005f7c4", "generation_seconds_batch": 16.481014234013855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9979298114776611, "target_z": 1.8828124732243834, "ce": 5.760505676269531, "genuineness": 4.300237655639648, "identity": 0.5308510065078735, "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/emo_Distress/fec1b833695c30433dea0b86dfd3b71cb6c1928a013f9931b61bb58fadeb3f55.mp3" }, { "id": "emo_Distress-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": "emo_Distress-en-0", "key": "ff1bf85d8cc1b457b3ae24b657b6480ae56b3b5ad3b438e6a3346df85f478820", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] The door is still open.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] I put your coat on the chair.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": "bbbcaa2cc15393877a9e69f411819fcbd9f0a400e5bf8cb0d82261103168ace1", "generation_seconds_batch": 21.18437027197797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22426070272922516, "target_z": -0.2871093731484946, "ce": 6.1894097328186035, "genuineness": 4.105680465698242, "identity": 0.45068520307540894, "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/emo_Distress/ff1bf85d8cc1b457b3ae24b657b6480ae56b3b5ad3b438e6a3346df85f478820.mp3" }, { "id": "emo_Distress-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": "emo_Distress-nl-1", "key": "ff38c93d2e5bc285e171af6286252c07235f80d21cad5f6f504cca99bcabe691", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Het stond naast het oude raam.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "54ab6efe4774115ba8fd5522b634b842bd5cfa49a75aaff2189fcb97e4b16d06", "generation_seconds_batch": 17.185673156986013, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8995640277862549, "target_z": 0.5390624481578485, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.6627299189567566, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast dat oude raam. We kunnen er 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/emo_Distress/ff38c93d2e5bc285e171af6286252c07235f80d21cad5f6f504cca99bcabe691.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-0", "key": "ffbf432e49b33f7137025bc4b49185da67df5ca6765136a91d45541919072e66", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] La porte est encore ouverte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 128, "seconds_generated": 10.24, "mp3_sha256": "a2d8a490315a7c4b19b42441477968a3bc9b56732c8561ffe468fc5506ec7f59", "generation_seconds_batch": 21.592975814943202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7297242879867554, "target_z": 1.5546875586784792, "ce": 5.673136234283447, "genuineness": 4.507347106933594, "identity": 0.5956811308860779, "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/emo_Distress/ffbf432e49b33f7137025bc4b49185da67df5ca6765136a91d45541919072e66.mp3" }, { "id": "emo_Distress-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": "emo_Distress-fr-1", "key": "fffcd6cae55c72fa3e8637d630c45e6b1376a614af20b9f83188111dec9cafbb", "bucket": "emo_Distress", "phase": "grid", "candidate": "manual-e66580c21865", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Emphasize vocal constriction and sharp intakes of breath to convey immediate panic. Pitch should fluctuate erratically with rising urgency.\nSCRIPT:\n(Start with a tight, constricted vocal delivery suggesting immediate pressure building internally.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Maintain rapid, shallow breathing patterns throughout the utterance, making the words feel rushed and breathless.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Conclude with a sudden, sharp vocal break or catch in the breath to signal complete emotional overflow.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "32cfafb2a7533ade61d4f7ccde43cd2f3ea102eb9d4b07d48b3571d0c04f5db2", "generation_seconds_batch": 22.78501379303634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4730606079101562, "target_z": 3.6875000136726555, "ce": 5.522225379943848, "genuineness": 3.9048471450805664, "identity": 0.5583915710449219, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons garder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "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/emo_Distress/fffcd6cae55c72fa3e8637d630c45e6b1376a614af20b9f83188111dec9cafbb.mp3" }, { "key": "original-emo_Distress-de-0-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "31b11998b324a0f0dd9975663807265becfd68822b9071eb06b5ffa5dad5c2f2", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.16040223836898804, "target_z": -0.3652343606152272, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.5685209035873413, "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/emo_Distress/de/52735c180817d0459d009d7a.mp3" }, { "key": "original-emo_Distress-de-0-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "9ab8bf391ba0de34e6336e42b240be8c0affe06963509cda16795497add1bf0f", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.17157745361328125, "target_z": -0.35156250740602163, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.4774836003780365, "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/emo_Distress/de/74348f187ac544c1f57eca8e.mp3" }, { "key": "original-emo_Distress-de-0-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "d235d859cc58158e07ccda55ea70522d1a72f8a6c1a43c450265eb3a3881e641", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.2035067081451416, "target_z": -0.31249998632734466, "ce": 6.3641486167907715, "genuineness": 4.494794845581055, "identity": 0.2170303463935852, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Manthe auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "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/emo_Distress/de/b4bc41788b16302d486d993b.mp3" }, { "key": "original-emo_Distress-de-0-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "93a531b58c415b3853c4f47d9f6804c677de113c6042225a78a2dc2006548466", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.2777421772480011, "target_z": -0.22167968315608347, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.6759122610092163, "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/emo_Distress/de/b40d4112a4fc6d3f899c8dab.mp3" }, { "key": "original-emo_Distress-de-0-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "b394aeba776a9be7cfc0c17e9833b138bb4d82a9c7db83baf771e3e77f21f71b", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.5396362543106079, "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/emo_Distress/de/754774ac57be29779951c83e.mp3" }, { "key": "original-emo_Distress-de-0-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "f149c87db7a0bd0e132df4ff03fe8643976ff18434ae6869410370cf34a9483d", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1428411602973938, "target_z": -0.3867187326243338, "ce": 6.229123115539551, "genuineness": 4.6203155517578125, "identity": 0.5752673745155334, "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/emo_Distress/de/2dffa4b0b9bcffc098915c21.mp3" }, { "key": "original-emo_Distress-de-0-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "9120b7a2f291e9d959610764fd6455282b3c74545b7c170dafb59451a50ee270", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.22745361924171448, "target_z": -0.2832031319787512, "ce": 6.2767791748046875, "genuineness": 4.68307638168335, "identity": 0.6674751043319702, "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/emo_Distress/de/eb4a2e6d3b8b6e38632f909c.mp3" }, { "key": "original-emo_Distress-de-0-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "4f97c467215e3b829c752375d8b7eb8bca5fb24d8871281f365f9808dcc40547", "task_id": "emo_Distress-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.20191022753715515, "target_z": -0.3144531342575271, "ce": 6.356205940246582, "genuineness": 4.758388519287109, "identity": 0.6445145010948181, "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/emo_Distress/de/c88034c08aec29331c81f3c5.mp3" }, { "key": "original-emo_Distress-de-1-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "689efc7e99cf463f0ed924bb9318d2c54d173753817914724b7c3319ced10c2e", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.419747352600098, "genuineness": 4.557555198669434, "identity": 0.40899714827537537, "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/emo_Distress/de/912d1db081ebe981439522ed.mp3" }, { "key": "original-emo_Distress-de-1-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "cb64564826588a98d0ae723f3497640efd2d9379e227da2b96e6d2c2b6adf660", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.07578974962234497, "target_z": -0.4687499977212241, "ce": 6.507116317749023, "genuineness": 4.457139015197754, "identity": 0.575752317905426, "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/emo_Distress/de/f1052ded9b2538c393fc1a1d.mp3" }, { "key": "original-emo_Distress-de-1-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "03654608ab23c37182495b4855bdd7c2ec3bb0ebdfeb33dca575c1d3a11e6243", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.05343928933143616, "target_z": -0.49609374060004946, "ce": 6.475345611572266, "genuineness": 4.293961524963379, "identity": 0.5140047669410706, "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/emo_Distress/de/e68d64e4ab0c5c03fa9b8de3.mp3" }, { "key": "original-emo_Distress-de-1-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "6a4dd237670a07fd5bf93fc0fd7fa15993eb28d58c3c8ae648d9190eb65f5aa0", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.08536851406097412, "target_z": -0.45703125598178673, "ce": 6.395919322967529, "genuineness": 4.444586753845215, "identity": 0.39138472080230713, "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/emo_Distress/de/7ef141ac19f63b49d3aa763d.mp3" }, { "key": "original-emo_Distress-de-1-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "ca16b934fb2eeb390ce503b225c60beb4fc9936289524d3b3f1c5a7c3666922a", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.06621098518371582, "target_z": -0.4804687394606615, "ce": 6.2767791748046875, "genuineness": 4.362998008728027, "identity": 0.42398926615715027, "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/emo_Distress/de/ec137c269f66fd96f096b645.mp3" }, { "key": "original-emo_Distress-de-1-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "06016a21e1c2e2d3eba936e9825e107c6e4ae336e60b04285e1103d16cac1ccb", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.10931545495986938, "target_z": -0.42773436517277896, "ce": 6.419747352600098, "genuineness": 4.519899368286133, "identity": 0.4723588824272156, "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/emo_Distress/de/5f260890bd9701772ddc2a8f.mp3" }, { "key": "original-emo_Distress-de-1-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "7314216d8eeeb35cff8d36a5d3c3db9498df8035da29cbb04047ac27be410d0a", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.03428173065185547, "target_z": -0.5195312605393385, "ce": 6.419747352600098, "genuineness": 4.256305694580078, "identity": 0.5759224891662598, "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/emo_Distress/de/01b3262364a9a1c8dc4e040a.mp3" }, { "key": "original-emo_Distress-de-1-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c05245eaef930bcdffcf54bf7d0e678db8125379331d17343c0345dd51e2347f", "task_id": "emo_Distress-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.050246357917785645, "target_z": -0.5, "ce": 6.507116317749023, "genuineness": 4.337893962860107, "identity": 0.5204644799232483, "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/emo_Distress/de/5acc4140458755b9cac0d9a3.mp3" }, { "key": "original-emo_Distress-en-0-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "42d29b483e26c38993bde0e3a96402fc379191e8219aa0607c296021cb0fd3a9", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.22426070272922516, "target_z": -0.2871093731484946, "ce": 6.2767791748046875, "genuineness": 4.137060642242432, "identity": 0.3910386562347412, "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/emo_Distress/en/bf550f3cacf5daa2f300f46a.mp3" }, { "key": "original-emo_Distress-en-0-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "6afc89f1a0aad5d5c9d58187522dbcc213ddf6d25ceca521b7f489b729ccb530", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.22106777131557465, "target_z": -0.29101563254844515, "ce": 6.284721851348877, "genuineness": 4.268857479095459, "identity": 0.4294862747192383, "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/emo_Distress/en/d8830b72a3346038f2009471.mp3" }, { "key": "original-emo_Distress-en-0-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "fda90b040f8147e16d8a62ccdbfb182734317e5c969e1b089ace97b03cb11353", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.09814020991325378, "target_z": -0.44140625484239876, "ce": 6.221180438995361, "genuineness": 3.9676074981689453, "identity": 0.40500256419181824, "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/emo_Distress/en/7fbb82b9832d683ae49d59ba.mp3" }, { "key": "original-emo_Distress-en-0-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c91a29cfff2be21c7b908665f67b4175cd749278b7bf85e3ba55d4a08dd6593f", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.19712084531784058, "target_z": -0.32031250512724574, "ce": 6.23706579208374, "genuineness": 4.193545341491699, "identity": 0.3410935699939728, "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/emo_Distress/en/f061656ef901513a6459d1db.mp3" }, { "key": "original-emo_Distress-en-0-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "ffcc7060ae1806443adcdefc18ef019e68674840d5a28cc568663cff3c868c8e", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.13326236605644226, "target_z": -0.3984375108241855, "ce": 6.260893821716309, "genuineness": 4.293961524963379, "identity": 0.14490537345409393, "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/emo_Distress/en/dec531fc3b0c8950e4672b01.mp3" }, { "key": "original-emo_Distress-en-0-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "2ef44b567919c953c835b31fa1cc8544ecde4fadd8d52e207efc0f351538c2d9", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1588057577610016, "target_z": -0.3671875085454096, "ce": 6.046441555023193, "genuineness": 3.5941832065582275, "identity": 0.3706393837928772, "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/emo_Distress/en/a567abc167c374e7525e8d6b.mp3" }, { "key": "original-emo_Distress-en-0-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "7023015336c3ae972eabfb76ed00c9e55fa3e7346715e23d2f12fe9af7586b30", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.20669960975646973, "target_z": -0.30859376338780836, "ce": 6.229123115539551, "genuineness": 4.168440818786621, "identity": 0.11783301830291748, "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/emo_Distress/en/09e00a8d3f07e27b1d2cb057.mp3" }, { "key": "original-emo_Distress-en-0-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "4a83c244ff380d4e14d22aa6c227b535a3dbafb114869febe17c27d22906c227", "task_id": "emo_Distress-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.2003137767314911, "target_z": -0.3164062457272952, "ce": 6.213237762451172, "genuineness": 4.243753433227539, "identity": 0.206371009349823, "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": 0.03999999999999915, "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/emo_Distress/en/16caff25532703e6f1c4f180.mp3" }, { "key": "original-emo_Distress-en-1-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "7df2929d490591e84f1a1fd60d542f6a4c1c210dd9ad4866942d4477b028a716", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.11410483717918396, "target_z": -0.4218749943030603, "ce": 6.395919322967529, "genuineness": 4.469690799713135, "identity": 0.5927865505218506, "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/emo_Distress/en/1d15dfcd23c61d73c5df16cd.mp3" }, { "key": "original-emo_Distress-en-1-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "b86db00d2be1f745ff97034de7bdc422ab0b63c46f4157e9e4fadbdccdd62a71", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.13645529747009277, "target_z": -0.39453125142423495, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.17802056670188904, "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/emo_Distress/en/d7e5df8bea6ab821c5fd7f7a.mp3" }, { "key": "original-emo_Distress-en-1-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "51db0b290c84cc75cf792ceeb3e9f6b03db396dcc8fcbebddffe2018a10698ce", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.06621098518371582, "target_z": -0.4804687394606615, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.6186800003051758, "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/emo_Distress/en/d6eb8eda8ff0f1739e3ced44.mp3" }, { "key": "original-emo_Distress-en-1-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "f158eec3eaba20f34ea62f789f233acf21ffe3f7b28a0dbca1ee49ba1a3af5e7", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.14603406190872192, "target_z": -0.3828125096847975, "ce": 6.284721851348877, "genuineness": 4.3127899169921875, "identity": 0.4498177170753479, "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/emo_Distress/en/222722ae058fe25641270947.mp3" }, { "key": "original-emo_Distress-en-1-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "fcc9d6ab2f67dffd5adb992cdda9dddce8b5ff2b33386ba750a14bb717afa658", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.11729776859283447, "target_z": -0.4179687349031097, "ce": 6.2767791748046875, "genuineness": 4.162164688110352, "identity": 0.4751478433609009, "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/emo_Distress/en/50eb61b089212e4d8f6a0ab0.mp3" }, { "key": "original-emo_Distress-en-1-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "4a8425e38413814705d0ba42876800db2b0b22c905ac72e2aedb551b1b911fb6", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.10452607274055481, "target_z": -0.4335937360424977, "ce": 6.173524379730225, "genuineness": 4.319066047668457, "identity": 0.4825241267681122, "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/emo_Distress/en/a9860f17f8afcba88944ec04.mp3" }, { "key": "original-emo_Distress-en-1-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "86213fd12145fd067bf34df6dad60644153d7fbd78d04158d699df7a2f4a0f35", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.05822867155075073, "target_z": -0.49023436973033074, "ce": 6.292664527893066, "genuineness": 4.099404335021973, "identity": 0.3789282739162445, "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/emo_Distress/en/c47c54d16b8b45afeecd9f6a.mp3" }, { "key": "original-emo_Distress-en-1-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "3493d54ac6c2978c3482eadbeb58b8dc1d4e43c30d50c77725667a813472a2e7", "task_id": "emo_Distress-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.09814020991325378, "target_z": -0.44140625484239876, "ce": 6.332377910614014, "genuineness": 4.419482707977295, "identity": 0.3508928418159485, "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/emo_Distress/en/ecb38374c584e934f31f4b12.mp3" }, { "key": "original-emo_Distress-es-0-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "4e6e61a1abf2f7e255a4568283acecc5c3b4b64e2789f3be9facd214ece6b3ae", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.230646550655365, "target_z": -0.2792968725788006, "ce": 6.038498878479004, "genuineness": 4.444586753845215, "identity": 0.6569730043411255, "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/emo_Distress/es/1a5b6828a74e701eb8d93b2a.mp3" }, { "key": "original-emo_Distress-es-0-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "16c32de2544be77b500756e287b08a00960c8bb93505cb5d5971c70756d635a1", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.09175437688827515, "target_z": -0.4492187371818856, "ce": 5.982900142669678, "genuineness": 4.030367851257324, "identity": 0.7603164911270142, "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/emo_Distress/es/c9607912f1c9cc5bec655f28.mp3" }, { "key": "original-emo_Distress-es-0-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "ba3a12f8f4f69a4c45c7a897c5e4ce2a8d82f7f07c47f81f1fdff243430d86ac", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.09335082769393921, "target_z": -0.4472656257121175, "ce": 6.149696350097656, "genuineness": 4.325342178344727, "identity": 0.5428398847579956, "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/emo_Distress/es/b6b990cc601a324fdad76d38.mp3" }, { "key": "original-emo_Distress-es-0-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "8115627a0f4f51d01ecd9922339dc61a9fc41989f0802da783ec8bf34b8952a9", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.11250835657119751, "target_z": -0.42382814223324267, "ce": 5.982900142669678, "genuineness": 4.1998209953308105, "identity": 0.6318134665489197, "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/emo_Distress/es/bdd669acdff452ef0583d316.mp3" }, { "key": "original-emo_Distress-es-0-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "ce38e5eda96447b4e7ab8bc559792a530d56b59e0e6106502bcd9e5b383908b2", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.13326236605644226, "target_z": -0.3984375108241855, "ce": 5.998785495758057, "genuineness": 4.042920112609863, "identity": 0.4060676395893097, "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/emo_Distress/es/be1d9ded70f82775684d3afc.mp3" }, { "key": "original-emo_Distress-es-0-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "d43644660b4da11a18f27ea8109188742bddae0521499bc3af2c5bfdf416a426", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.12687653303146362, "target_z": -0.40624999316367233, "ce": 6.038498878479004, "genuineness": 4.268857479095459, "identity": 0.5375087857246399, "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/emo_Distress/es/fcbdaad6c59d88bbc52fd65b.mp3" }, { "key": "original-emo_Distress-es-0-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "760f538256d0091d423dcc1619a04df8c625754b485591cf040d978566f7e946", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.149696350097656, "genuineness": 4.243753433227539, "identity": 0.47814857959747314, "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/emo_Distress/es/88026b4636d00955368b1e5a.mp3" }, { "key": "original-emo_Distress-es-0-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo estás listo.", "directions": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "cbadd6406d1579c21c774261b711e042142f09ae605f6ef7a2058241eb3c1ee6", "task_id": "emo_Distress-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La puerta sigue abierta.\n(Intense Distress. 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(Intense Distress. 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": 0.11889421939849854, "target_z": -0.4160156234333416, "ce": 5.895530700683594, "genuineness": 4.011539936065674, "identity": 0.5976710915565491, "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/emo_Distress/es/e5b8c06a32509d85a80c91c8.mp3" }, { "key": "original-emo_Distress-es-1-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "f05219d996b45efe626b02ecb159b6d5c261374deb893aae6272cb3d43979b13", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.1013331413269043, "target_z": -0.4374999954424482, "ce": 6.117925643920898, "genuineness": 4.545003414154053, "identity": 0.6187469959259033, "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/emo_Distress/es/ad9d3d04c21703586279a3ca.mp3" }, { "key": "original-emo_Distress-es-1-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "512c1ec7b5e03addf89d5876b19328e557e014b898142c2c150a9dceba70fb0d", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.09175437688827515, "target_z": -0.4492187371818856, "ce": 6.09409761428833, "genuineness": 4.632867813110352, "identity": 0.6240159273147583, "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/emo_Distress/es/de58741870327ba6af47d2a4.mp3" }, { "key": "original-emo_Distress-es-1-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "a28388b237434ac496de52cd21833945dba8ea1e569091faa281b9ffd013a8b8", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.059825122356414795, "target_z": -0.4882812582605626, "ce": 6.197352409362793, "genuineness": 4.532451152801514, "identity": 0.5094583034515381, "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/emo_Distress/es/a7cb7c3ecc274e993c2bd324.mp3" }, { "key": "original-emo_Distress-es-1-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "dbaf9301016981fbeabdba2deb0672d0aac13e53d535c90185578876e918e5b1", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.14922699332237244, "target_z": -0.378906250284847, "ce": 5.764476776123047, "genuineness": 3.961331605911255, "identity": 0.46584537625312805, "hypothesis": "He encontrado la con tu mentila aquí ne ha carido shi of la cajita que zingo negos pertines", "wer": 0.8235294117647058, "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/emo_Distress/es/08d93c410d554bb21ef58000.mp3" }, { "key": "original-emo_Distress-es-1-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "7acb2c1d5b1e001842834177891bbbe801c30067ab916042d7ee96140034e531", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.11570128798484802, "target_z": -0.4199218828332921, "ce": 6.229123115539551, "genuineness": 4.7081804275512695, "identity": 0.49953556060791016, "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/emo_Distress/es/4ef54fa3f19013ffeb0396fb.mp3" }, { "key": "original-emo_Distress-es-1-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "b363bbf7ea26b1acf58a2f864199f60885257af2bf2ef81ba6796d49379fb8d3", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.13006946444511414, "target_z": -0.4023437337637218, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.5433404445648193, "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/emo_Distress/es/cdfd5b1a1a110402722af241.mp3" }, { "key": "original-emo_Distress-es-1-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "5c0052b5ed19331347648bf8f52a5a5b6dd086d48b4a69c2be05b4f5e580d805", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.15561282634735107, "target_z": -0.37109376794536014, "ce": 6.086154937744141, "genuineness": 4.846253395080566, "identity": 0.6578283309936523, "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/emo_Distress/es/14f4b21038fad781607e619a.mp3" }, { "key": "original-emo_Distress-es-1-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "4701d2fdfeda3e9bd968ea4f2f1e6e379184ea4cb1c46938d7b3e12d8b961ea7", "task_id": "emo_Distress-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] He encontrado la cajita.\n(Intense Distress. 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(Intense Distress. 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": 0.040667593479156494, "target_z": -0.5117187417394374, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.6504759788513184, "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/emo_Distress/es/c246a85f8304eb583f32691a.mp3" }, { "key": "original-emo_Distress-fr-0-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "71ca3e664d737c8a8f4fa12e7ed0a4e8ac5f13d75f438d9f8f3cb7835959d962", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.14763054251670837, "target_z": -0.38085936175461516, "ce": 6.078212261199951, "genuineness": 4.319066047668457, "identity": 0.4375830590724945, "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/emo_Distress/fr/f2f065699fe5c92c8a63e08f.mp3" }, { "key": "original-emo_Distress-fr-0-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "8ab541af56b0e0ae3dcec9449106f09ee02bb2ce63a9ec359c476ac379a8ba90", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.17477038502693176, "target_z": -0.3476562480060711, "ce": 5.967014789581299, "genuineness": 4.243753433227539, "identity": 0.8004732728004456, "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/emo_Distress/fr/2943c002fd613cb02614b3c0.mp3" }, { "key": "original-emo_Distress-fr-0-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c3e51dc493f7b8e3b647f4dedcce4e6f757d06f51d1a7e561f9588980cf7664d", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1619986891746521, "target_z": -0.36328124914545906, "ce": 6.125868320465088, "genuineness": 4.381826400756836, "identity": 0.7148178815841675, "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/emo_Distress/fr/09ff5058fb9959e3bd0ebd82.mp3" }, { "key": "original-emo_Distress-fr-0-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "6237ce52b500b95256e15d28bce50b7882e6a8700b1887aa4bb7d191206940f4", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.022613525390625, "genuineness": 4.118232727050781, "identity": 0.8014237880706787, "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/emo_Distress/fr/d1fe378b074c2d95c644cd1a.mp3" }, { "key": "original-emo_Distress-fr-0-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c32c05b5faacc0e2c30341c8507c252b10be5cbc2e03ee86b0603505e056ea82", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1316659152507782, "target_z": -0.4003906222939536, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.6663171648979187, "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/emo_Distress/fr/9ebdbde64044067e7b980fb4.mp3" }, { "key": "original-emo_Distress-fr-0-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "f245068d0e852c2004794c2aef97b44c2b7671d0d14c9b16ddf6ba1b97e457e9", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.17157745361328125, "target_z": -0.35156250740602163, "ce": 5.9431867599487305, "genuineness": 4.306513786315918, "identity": 0.7991620302200317, "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/emo_Distress/fr/3fc7c3d12314b23c9ff26a43.mp3" }, { "key": "original-emo_Distress-fr-0-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "bacf118dafbabff08e6ce3f96972df816624478220b8593c654c837de0a89a35", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.2003137767314911, "target_z": -0.3164062457272952, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.5450180768966675, "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/emo_Distress/fr/a6a56d08dad4e8e34c3d93d8.mp3" }, { "key": "original-emo_Distress-fr-0-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "68219ef2562c2aec315025d7c3a8ba01f3700eae381e3bb2ebd8a10478a26583", "task_id": "emo_Distress-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.16838452219963074, "target_z": -0.35546876680597217, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.7054029107093811, "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/emo_Distress/fr/dffdf5bfbc737ae9a3fa75be.mp3" }, { "key": "original-emo_Distress-fr-1-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "3f3ccd344d657de8e5d980cb3b3e2cfc9edb3e6404355746b0c8cdefd62c393c", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.07898268103599548, "target_z": -0.46484373832127357, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.7908366918563843, "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/emo_Distress/fr/520cdc666460dc1464fcdd7b.mp3" }, { "key": "original-emo_Distress-fr-1-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "35bdae839167e245bfdfa578dc1da06113cd98e5e305f08257630449a7253dc8", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.11729776859283447, "target_z": -0.4179687349031097, "ce": 6.062326908111572, "genuineness": 4.507347106933594, "identity": 0.6040567755699158, "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/emo_Distress/fr/440451f4b37c50e0d3d0a2f8.mp3" }, { "key": "original-emo_Distress-fr-1-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "a8826f75a3ddc61dcad1591aa1448ba8a6a2736dfbc68aee8136e86ed9e9a667", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1651916205883026, "target_z": -0.3593749897455085, "ce": 6.260893821716309, "genuineness": 4.632867813110352, "identity": 0.6783838868141174, "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/emo_Distress/fr/c701da9fd48784b88361c4c7.mp3" }, { "key": "original-emo_Distress-fr-1-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "568d600bafa876dd99494466fbb1dd5a30dc647e66e8c535125b9685279ce2de", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.12368360161781311, "target_z": -0.41015625256362287, "ce": 6.173524379730225, "genuineness": 4.545003414154053, "identity": 0.7361443042755127, "hypothesis": "J'ai trouvé J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "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/audio/emo_Distress/fr/11eb183455422a0ade6d9ead.mp3" }, { "key": "original-emo_Distress-fr-1-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "8d91c195247a555d0d15bb162de2b15f9bf4a166c54fb4025649ce4696702c35", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.16838452219963074, "target_z": -0.35546876680597217, "ce": 6.109982967376709, "genuineness": 4.645420074462891, "identity": 0.6334701776504517, "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/emo_Distress/fr/a8ca8dc02efaf2eba912b355.mp3" }, { "key": "original-emo_Distress-fr-1-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "6fd5a7ed4d73f20219b561ed0d7bf76ccbdcbb4258d170fe1c9eeedafa3fd392", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.10452607274055481, "target_z": -0.4335937360424977, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.6361346244812012, "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/emo_Distress/fr/03d3d7297bec3980a60e0575.mp3" }, { "key": "original-emo_Distress-fr-1-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "b3f1d2a08499ad7822d8a9b689751da20ef4083c0f93a97aa2676dba0ffd5c76", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1428411602973938, "target_z": -0.3867187326243338, "ce": 6.141753673553467, "genuineness": 4.469690799713135, "identity": 0.8543452620506287, "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/emo_Distress/fr/22c90e04fc180f094297064d.mp3" }, { "key": "original-emo_Distress-fr-1-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "dfb1b022c689b0d1f60c212bc0afcd58c5b10f956cf9e365c1af907dd0e3998f", "task_id": "emo_Distress-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.14922699332237244, "target_z": -0.378906250284847, "ce": 6.157639026641846, "genuineness": 4.7458367347717285, "identity": 0.8129372596740723, "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/emo_Distress/fr/59edffc419a8bf49a9e78dfc.mp3" }, { "key": "original-emo_Distress-nl-0-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "2d35fbb3e6492453af3c1cfb2428f1ef003798412019fcdab54940c9ed840ab7", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.6010257005691528, "target_z": 0.17382812400303554, "ce": 6.173524379730225, "genuineness": 4.344170093536377, "identity": 0.6635025143623352, "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/emo_Distress/nl/3cf63ff78551b986b36033ad.mp3" }, { "key": "original-emo_Distress-nl-0-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c4922c17546950e77a5232f4545ecb6211459008f0764c5aaa145497f4dab092", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.3934856653213501, "target_z": -0.08007811716670787, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.7079572081565857, "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/audio/emo_Distress/nl/a623c03c7a3c2e4f716da054.mp3" }, { "key": "original-emo_Distress-nl-0-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "0bad34185902b296100d02af437f5417d59bd080b905fbc4917a516502d9fa30", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.3408024311065674, "target_z": -0.1445312331940278, "ce": 6.109982967376709, "genuineness": 4.250029563903809, "identity": 0.7307384014129639, "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/emo_Distress/nl/5a5f45c718ededceec0e6561.mp3" }, { "key": "original-emo_Distress-nl-0-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "a3c3bf10e3f3e12f7d9375cf3a96c3f9671773b71d8b8c81bce148c62e3d17a0", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.5986310243606567, "target_z": 0.1708984567983833, "ce": 6.141753673553467, "genuineness": 4.325342178344727, "identity": 0.575761616230011, "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/emo_Distress/nl/9772e980b1cc08d1a7bffbce.mp3" }, { "key": "original-emo_Distress-nl-0-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "92f07a87c70cd1b10bf4c1b087fb4dfd60dca0941956a3459cf08ad9d72197ed", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.3104696273803711, "target_z": -0.18164064280293662, "ce": 6.109982967376709, "genuineness": 4.168440818786621, "identity": 0.7452579736709595, "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/emo_Distress/nl/9e66ba858e5d47787aeebcf2.mp3" }, { "key": "original-emo_Distress-nl-0-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "c8810610842d9775ea9b29df7f5eb29083f273526a00f0630f0b2e3fa719c661", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.2561899423599243, "target_z": -0.24804687030002473, "ce": 6.062326908111572, "genuineness": 4.168440818786621, "identity": 0.5963494777679443, "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/emo_Distress/nl/beb9fa78eaf88525b3c400be.mp3" }, { "key": "original-emo_Distress-nl-0-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "b84d06ef165c7fec9b763c0cb2e2d535bc4ad8bbdccdcaf470015cce4467291c", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.24022531509399414, "target_z": -0.2675781308393632, "ce": 5.752562999725342, "genuineness": 4.074300289154053, "identity": 0.6611728668212891, "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/audio/emo_Distress/nl/776f21a48d2158acc6c83c52.mp3" }, { "key": "original-emo_Distress-nl-0-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "1f9c3008491c980749cab451a6216be58eb563d5f73da94b63ede2a9786c3f41", "task_id": "emo_Distress-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.47490522265434265, "target_z": 0.01953126053933849, "ce": 6.205295085906982, "genuineness": 4.20609712600708, "identity": 0.6234679222106934, "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/emo_Distress/nl/43b8938f822239a755e06e09.mp3" }, { "key": "original-emo_Distress-nl-1-seed1701-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "40b2f7203c11b57962654c2292ecef843ba9ca725f13c8b97d84a8c71321c1dd", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.12368360161781311, "target_z": -0.41015625256362287, "ce": 6.1020402908325195, "genuineness": 4.218649387359619, "identity": 0.5319312810897827, "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/emo_Distress/nl/0cc37dd5f4e7539dabbffa27.mp3" }, { "key": "original-emo_Distress-nl-1-seed1701-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "445b8bc43ff07f4e9f1984698712add10dbf7db8e9551d2d8b804bb13e531b2b", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.19392791390419006, "target_z": -0.3242187645271963, "ce": 6.09409761428833, "genuineness": 4.105680465698242, "identity": 0.7069377899169922, "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/emo_Distress/nl/4dcdb8403449cb91ae7dd5dc.mp3" }, { "key": "original-emo_Distress-nl-1-seed1701-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "3aa6f8ddc2da2a3a27da1fe6c580cc9b4585231cb92b3cd69b870d9db5040592", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.7782329320907593, "target_z": 0.39062495556387017, "ce": 6.173524379730225, "genuineness": 4.030367851257324, "identity": 0.6188225150108337, "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/audio/emo_Distress/nl/8aba01b060ca65e6b56ef6d8.mp3" }, { "key": "original-emo_Distress-nl-1-seed1701-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "6c75ae808377fceb0b746b62bff7bcfb6f3636faba996f557ac475c21ffe064e", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.3519776463508606, "target_z": -0.13085937998482225, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.5996413230895996, "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/emo_Distress/nl/24346767bce228478b3c4804.mp3" }, { "key": "original-emo_Distress-nl-1-seed1702-scale0.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "95de013b78bfd4eaf60c35e1731da15b892af43aaeb04ddc2415a1388b34ebf4", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.006728172302246, "genuineness": 4.344170093536377, "identity": 0.35764312744140625, "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/emo_Distress/nl/92965c191494c6f24f994923.mp3" }, { "key": "original-emo_Distress-nl-1-seed1702-scale0.5", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "ec8582107695dfc8ca8d409a549ddc3ec158731f21ddaac529375975b325b483", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.25698816776275635, "target_z": -0.24707031456514064, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.632744550704956, "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/emo_Distress/nl/7dab1ea5830d5ae7dbda0e3a.mp3" }, { "key": "original-emo_Distress-nl-1-seed1702-scale0.75", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "90dfce7702e80d5cdff33a002e76c379591df68941d44bec5b02f72a94e1dab5", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.25938284397125244, "target_z": -0.2441406473604884, "ce": 6.125868320465088, "genuineness": 4.362998008728027, "identity": 0.5995051264762878, "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/emo_Distress/nl/c663431e04c65920ccf4ec1c.mp3" }, { "key": "original-emo_Distress-nl-1-seed1702-scale1.0", "bucket": "emo_Distress", "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. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": [ "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Distress. 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": "d91b3f283f49d0b22ebb3537b9bd8b8e1252fba78dacd98e62fc1362c4186db7", "mp3_sha256": "1f71ba48b38b59dd70f81b5a3b9e7305030a50c9048a9af73cc9408bb213983c", "task_id": "emo_Distress-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Distress. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Distress. 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(Intense Distress. 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(Intense Distress. 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": 0.1811562180519104, "target_z": -0.33984376566658425, "ce": 6.165581703186035, "genuineness": 4.118232727050781, "identity": 0.744641900062561, "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/emo_Distress/nl/c83846503123d62180632182.mp3" } ], "source_standard_audio_unchanged": true }